© 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. 11185
    Prev
    Next
    INDEX
    Explanations

    some + adjective/more/of

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

    some of

    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
    O
    0.64
    ۰
    0.57
    delt
    0.56
    ชนิด
    0.55
     kroppen
    0.54
    B
    0.54
    P
    0.52
    G
    0.52
     Dijk
    0.51
     K
    0.51
    POSITIVE LOGITS
    ס
    0.80
    л
    0.78
     or
    0.67
     on
    0.65
     as
    0.64
     of
    0.63
    ল
    0.57
     amazingly
    0.55
     financement
    0.55
    ás
    0.54
    Activations Density 0.170%

    No Known Activations