© 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. 225723
    Prev
    Next
    INDEX
    Explanations

    CAD, CAE, CAM

    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
    _),
    0.47
    stri
    0.47
    warnings
    0.45
    ),
    0.44
    rint
    0.44
     coloured
    0.43
    inin
    0.42
     ܐ
    0.42
    이를
    0.41
    》(
    0.41
    POSITIVE LOGITS
    лли
    0.48
     curve
    0.48
    łoż
    0.47
    フィールド
    0.47
    esquerda
    0.47
    ोदय
    0.46
    蹶
    0.46
     storico
    0.46
     ያ
    0.46
    Bezier
    0.46
    Activations Density 0.000%

    No Known Activations