© 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. 245871
    Prev
    Next
    INDEX
    Explanations

    made verbal

    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
    を使用
    0.49
     phenomena
    0.46
    証
    0.44
    標
    0.43
    罫
    0.42
    或其他
    0.42
    澤
    0.42
     interconnection
    0.42
    ㎥
    0.42
    ','$
    0.41
    POSITIVE LOGITS
     الحكم
    0.46
     wiadomo
    0.45
     Aktiv
    0.43
    僌
    0.43
    ن
    0.42
     നല്ല
    0.41
     sprung
    0.40
    뉴스
    0.40
     ঘো
    0.40
     органів
    0.40
    Activations Density 0.001%

    No Known Activations