© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10267
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Champions
    0.72
     Contractors
    0.71
     Accepting
    0.71
     ヘア
    0.70
    يمكن
    0.69
    ों
    0.69
     Habits
    0.68
    नाइटेड
    0.68
    も
    0.68
     Engaging
    0.67
    POSITIVE LOGITS
    此前
    0.77
    Mai
    0.73
    subplot
    0.72
    ፨
    0.72
    볐
    0.72
    ৭
    0.72
    Tweet
    0.71
    স্থানীয়
    0.71
    layout
    0.70
     laug
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.