© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7013
    Prev
    Next
    INDEX
    Explanations

    validity of options

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

    The neuron activates on occurrences of “valid” (and its related forms like “validity”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -2.39
     Reſ
    -2.13
     \'
    -2.09
    謇
    -2.08
    งิน
    -2.06
    
    -1.98
    
    -1.94
     Conſ
    -1.93
    惴
    -1.93
     ´
    -1.92
    POSITIVE LOGITS
    As
    2.08
    1
    2.05
     and
    2.02
    Y
    1.98
    Even
    1.84
    lgari
    1.80
    In
    1.79
    ﹍﹍
    1.77
    4
    1.76
    é
    1.74
    Activations Density 0.009%

    No Known Activations