© 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. 243700
    Prev
    Next
    INDEX
    Explanations

    candidates follow, special hunts, diet

    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
    動作
    0.47
    nt
    0.46
     In
    0.46
    str
    0.46
     MUS
    0.46
    ll
    0.44
     ঘিরে
    0.44
    ع
    0.44
     designers
    0.43
     dishes
    0.43
    POSITIVE LOGITS
     مذہ
    0.49
     بابەت
    0.46
     ито
    0.44
     رجسٹر
    0.43
     খাত
    0.43
    第壹百
    0.42
     політи
    0.42
     upperBound
    0.41
    MakeRect
    0.41
     راجسټریشن
    0.41
    Activations Density 0.001%

    No Known Activations