© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78369
    Prev
    Next
    INDEX
    Explanations

    full

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly responds to words or morphemes meaning “whole/complete” (e.g. English “full” or Chinese “全”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "full" in Chinese text or technical documentation, particularly when it appears in compound terms or phrases.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language that denotes completeness or entirety, often used as a modifier or prefix indicating something is full/whole/entire.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     към
    -0.71
    ственное
    -0.71
    webservice
    -0.66
    Greeting
    -0.66
     Henry
    -0.65
    diverse
    -0.65
    sri
    -0.65
    Chai
    -0.64
     îles
    -0.64
    anzibar
    -0.63
    POSITIVE LOGITS
    全
    0.97
    process
    0.92
    Process
    0.91
     全
    0.91
     process
    0.90
    过程
    0.86
    的全
    0.86
     processes
    0.85
    細節
    0.84
    ograft
    0.81
    Activations Density 0.012%

    No Known Activations