© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5511
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ه
    1.11
    駿
    0.86
    گی
    0.84
    гія
    0.83
     SLASH
    0.83
    dioxide
    0.81
    ді
    0.81
     CHALL
    0.80
    Surname
    0.80
     ELSE
    0.80
    POSITIVE LOGITS
    el
    0.82
     lamented
    0.78
    in
    0.74
    \;\
    0.74
     quais
    0.72
     celestial
    0.72
     sequester
    0.71
     renegoti
    0.69
     newspaper
    0.67
    वर्ड
    0.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.