© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208520
    Prev
    Next
    INDEX
    Explanations

    earlier, mentioned, just before

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

    identity and state descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ادي
    0.47
    蠍
    0.46
    ក្នុង
    0.45
    』（
    0.45
    ventures
    0.45
    angels
    0.44
    DNN
    0.44
     ምስ
    0.44
     червня
    0.44
    сці
    0.43
    POSITIVE LOGITS
     Ş
    0.57
     S
    0.56
     Commentary
    0.56
     P
    0.54
     Father
    0.52
     R
    0.52
     Rich
    0.52
     George
    0.52
     NYC
    0.52
     Y
    0.50
    Activations Density 0.000%

    No Known Activations