© 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. 45987
    Prev
    Next
    INDEX
    Explanations

    conditions or exceptions

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

    membership, timeframe, club

    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
    👿
    0.43
     economists
    0.43
     گرفتار
    0.41
    #$%
    0.41
    name
    0.40
    code
    0.40
    findIndex
    0.40
     মর
    0.39
     economist
    0.39
     aparent
    0.39
    POSITIVE LOGITS
    罨
    0.54
     பாதுகாப்பு
    0.50
     ответственности
    0.46
     czynności
    0.46
    翛
    0.46
    สามารถ
    0.44
    因为它
    0.43
    衽
    0.43
    সংযোগ
    0.42
     połą
    0.42
    Activations Density 0.000%

    No Known Activations