© 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. 150908
    Prev
    Next
    INDEX
    Explanations

    business names and descriptions

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

    virtual meetings or more money

    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
     dereg
    0.53
     дали
    0.50
    BOT
    0.45
     راست
    0.42
    PRI
    0.42
     Construction
    0.42
     前
    0.42
     Borel
    0.42
    Vote
    0.42
    Went
    0.41
    POSITIVE LOGITS
    يمي
    0.50
    reihe
    0.45
    راهيم
    0.45
    დ
    0.44
    zugs
    0.44
    وسي
    0.43
    dden
    0.43
     hanged
    0.43
    ק
    0.43
    direccion
    0.43
    Activations Density 0.000%

    No Known Activations