© 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. 112988
    Prev
    Next
    INDEX
    Explanations

    knownspares mepic letstranded sectionshonoured giveout someshould itroads andhave utilised

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

    technical contexts and specific instructions

    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
    asının
    0.55
     अनुदान
    0.49
     Grenoble
    0.49
    /**/*.
    0.47
     preoperative
    0.46
    nj
    0.46
     prepayment
    0.46
    asında
    0.45
    nostic
    0.45
     कंटिन्यू
    0.45
    POSITIVE LOGITS
    遢
    0.44
     групп
    0.41
    APPRO
    0.41
     इन्हे
    0.40
    ！）
    0.40
    猖
    0.39
     lacs
    0.38
    ра
    0.38
    တယ်။
    0.38
    テー
    0.38
    Activations Density 0.001%

    No Known Activations