© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55490
    Prev
    Next
    INDEX
    Explanations

    personal enjoyment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '।
    0.82
    '
    0.79
    koľ
    0.73
     hepatocellular
    0.73
    ’
    0.72
    "।
    0.70
     CheckException
    0.70
    एस
    0.69
     fühlen
    0.69
     இதன்
    0.68
    POSITIVE LOGITS
    the
    1.27
    ਰ
    1.16
    ва
    1.14
    it
    1.04
    ما
    1.02
    و
    0.99
    મ
    0.95
    ס
    0.93
    ور
    0.92
    a
    0.89
    Activations Density 0.010%

    No Known Activations