© 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. 182618
    Prev
    Next
    INDEX
    Explanations

    conditions periods Administrator specifies

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

    legal and security communications

    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
    InEx
    0.50
    žil
    0.50
    秭
    0.47
    Xs
    0.46
    烣
    0.46
    Indexes
    0.46
    #,
    0.45
     &/
    0.45
    FieldNumber
    0.44
    ing
    0.44
    POSITIVE LOGITS
    駆動
    0.55
    非常に
    0.51
    鯛
    0.48
    可能性がある
    0.45
    収
    0.45
     доступ
    0.44
    با
    0.44
    アクセス
    0.44
    約
    0.44
     biopsy
    0.44
    Activations Density 0.001%

    No Known Activations