© 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. 159700
    Prev
    Next
    INDEX
    Explanations

    charcoal black

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

    list items or points

    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
    オ
    0.54
    多
    0.53
     Moura
    0.51
    ６
    0.51
    カーボン
    0.50
    タ
    0.50
     ＊
    0.50
    О
    0.48
     ダ
    0.48
    Vend
    0.47
    POSITIVE LOGITS
     Deuteronomy
    0.48
     jar
    0.47
    ⊢
    0.46
     plots
    0.45
     컴퓨
    0.45
    irt
    0.45
     polygon
    0.45
    iter
    0.44
     plt
    0.44
    ^{-/-}$
    0.44
    Activations Density 0.000%

    No Known Activations