© 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. 143057
    Prev
    Next
    INDEX
    Explanations

    participation, separation, product

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

    questions and statements

    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
     explor
    0.56
     Il
    0.54
     Dana
    0.54
     Estatal
    0.54
     Win
    0.52
     t
    0.51
     nx
    0.51
     Explor
    0.50
     w
    0.50
     Euro
    0.50
    POSITIVE LOGITS
    sourceEncoding
    0.50
    hmC
    0.49
    हिमा
    0.47
    sruhe
    0.47
    ças
    0.44
    räge
    0.44
    but
    0.44
    fmt
    0.44
    หาคม
    0.44
    かどうか
    0.44
    Activations Density 0.001%

    No Known Activations