© 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. 97530
    Prev
    Next
    INDEX
    Explanations

    graph implementation

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

    code-related punctuation

    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
    toothbrush
    0.50
    ཎ
    0.48
    kun
    0.48
    တို့ကို
    0.48
     handlebar
    0.48
    kunft
    0.47
     shoal
    0.46
     ライン
    0.46
     ១
    0.45
    kében
    0.45
    POSITIVE LOGITS
    在
    0.52
    IfNeeded
    0.49
    ু
    0.48
    挾
    0.45
     estab
    0.45
    os
    0.44
    ใน
    0.44
    เผ
    0.42
     termino
    0.42
    도
    0.41
    Activations Density 0.000%

    No Known Activations