© 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. 245628
    Prev
    Next
    INDEX
    Explanations

    to offeringstep rehabpassed throughday useeven though

    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
     seguenti
    0.47
    setObjectName
    0.46
     تبلی
    0.45
     роках
    0.45
    CacheV
    0.45
     ở
    0.45
     э
    0.44
     bogus
    0.44
     Zusammenhang
    0.44
     zid
    0.44
    POSITIVE LOGITS
    ोले
    0.51
    iniai
    0.50
    Dropdown
    0.44
    ותר
    0.43
    email
    0.43
    镛
    0.42
    }(
    0.41
    クラブ
    0.41
    Hari
    0.41
    ДЕ
    0.41
    Activations Density 0.001%

    No Known Activations