© 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. 254615
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    t
    0.56
    ub
    0.48
    except
    0.48
    Reg
    0.44
    a
    0.44
    ی
    0.43
    test
    0.43
    ycz
    0.42
    ^
    0.42
    jena
    0.42
    POSITIVE LOGITS
    上帝
    0.45
     منصور
    0.45
    سٹر
    0.42
     automático
    0.42
     maliciously
    0.41
     ದೇವರ
    0.40
    パナソニック
    0.40
     služby
    0.40
     السياسي
    0.40
     fondateur
    0.40
    Activations Density 0.000%

    No Known Activations