© 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. 117063
    Prev
    Next
    INDEX
    Explanations

    direct or consequential

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

    absolute false completion salt

    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
     綿
    0.53
     vacanam
    0.53
    小時
    0.52
    細菌
    0.48
     因為
    0.47
     ポリエステル
    0.46
     ビタミン
    0.46
     jauh
    0.46
     bactéries
    0.46
     coniferous
    0.46
    POSITIVE LOGITS
    man
    0.54
    ി
    0.50
     Sett
    0.47
    os
    0.45
    un
    0.45
    or
    0.44
    vo
    0.44
     Settlements
    0.43
    il
    0.43
    hurt
    0.43
    Activations Density 0.000%

    No Known Activations