© 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. 166105
    Prev
    Next
    INDEX
    Explanations

    long pattern, solutions now, district municipality, campus culture

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

    code-related punctuation

    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
     comportamenti
    0.48
    巌
    0.48
    ერ
    0.47
    THUR
    0.47
    טל
    0.46
    ना
    0.46
    น
    0.46
    পো
    0.46
     വന്ന
    0.46
    कारा
    0.45
    POSITIVE LOGITS
    ist
    0.55
     relegation
    0.53
     εύ
    0.52
     მხ
    0.50
    omena
    0.49
    istem
    0.48
    lys
    0.48
     dual
    0.46
    omme
    0.46
    istu
    0.45
    Activations Density 0.000%

    No Known Activations