© 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. 22-GEMMASCOPE-RES-131K
    7. 26518
    Prev
    Next
    INDEX
    Explanations

    specific function names or roles

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

    The neuron fires strongly on tokens that introduce or accompany numeric, quantitative, or enumerated factual details in a text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    supset
    -1.02
    digans
    -0.97
     large
    -0.95
     huge
    -0.95
    ranton
    -0.92
     acheteurs
    -0.91
    вні
    -0.89
     of
    -0.89
    ніше
    -0.88
     フラワー
    -0.87
    POSITIVE LOGITS
     simple
    2.05
     small
    1.68
     basit
    1.67
    simple
    1.67
     jednoduch
    1.64
     semplice
    1.62
     simplicity
    1.61
     Simple
    1.59
    简单
    1.56
     simplest
    1.56
    Activations Density 0.302%

    No Known Activations