© 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. 210727
    Prev
    Next
    INDEX
    Explanations

    oven-proof ceramic

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

    generating insights

    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
    Liste
    0.51
    타
    0.50
    𝗷
    0.49
    ግሎ
    0.48
    ブ
    0.48
    薬
    0.47
    権
    0.47
    恋
    0.46
    律
    0.45
    組み
    0.45
    POSITIVE LOGITS
     HELP
    0.54
    রের
    0.52
     HOME
    0.52
     Homemade
    0.52
     lf
    0.51
    hne
    0.49
     Swimming
    0.49
    lf
    0.49
     TOTAL
    0.48
    h
    0.48
    Activations Density 0.000%

    No Known Activations