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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23715
    Prev
    Next
    INDEX
    Explanations

    questions and descriptions

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

    The neuron flags product‐review style mentions—especially specialized gear names and their technical attributes.

    oai_token-act-pair · o4-miniTriggered 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
     airports
    -0.84
     Airports
    -0.84
    água
    -0.84
     Palembang
    -0.83
    Jegyzőkönyv
    -0.83
     muualla
    -0.80
     homemade
    -0.80
     Muda
    -0.79
    cosx
    -0.79
     Homemade
    -0.78
    POSITIVE LOGITS
     stable
    0.75
    peh
    0.74
     reform
    0.72
    clickable
    0.71
     fore
    0.71
    dine
    0.71
    hsh
    0.69
    的角色
    0.68
    jss
    0.68
     medium
    0.67
    Activations Density 0.005%

    No Known Activations