© 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. 36822
    Prev
    Next
    INDEX
    Explanations

    primary duty

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

    parenthetical remarks

    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
    ي
    0.46
    يون
    0.45
    স্বাস্থ্য
    0.44
    地方
    0.44
     Presse
    0.44
     Diversity
    0.43
     Política
    0.43
    犯罪
    0.43
     Debido
    0.43
     tội
    0.43
    POSITIVE LOGITS
    MGMT
    0.47
     ഈ
    0.46
     ид
    0.46
     piss
    0.46
     appBar
    0.45
     imparts
    0.45
     ilang
    0.45
    ppel
    0.44
    エク
    0.43
    vaegir
    0.42
    Activations Density 0.001%

    No Known Activations