© 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. 158429
    Prev
    Next
    INDEX
    Explanations

    website owner

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

    evaluations, goals, rates

    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
     システム
    0.46
    orthogonal
    0.46
    ecd
    0.45
     東京
    0.45
    𝐌
    0.45
     inhomogeneities
    0.44
     terza
    0.44
     ошибок
    0.44
     occurrences
    0.44
     その他
    0.44
    POSITIVE LOGITS
    泵
    0.50
     Congressman
    0.48
     Pumps
    0.46
     Prosecutor
    0.45
     gasto
    0.45
     pumps
    0.44
     ګرځ
    0.44
     Leitung
    0.43
     Sheila
    0.42
    里的
    0.41
    Activations Density 0.002%

    No Known Activations