© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 15571
    Prev
    Next
    INDEX
    Explanations

    skeletons fight

    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_16_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
    in
    0.97
    ۰
    0.96
    t
    0.95
    the
    0.93
    ین
    0.89
    f
    0.89
    d
    0.81
    inna
    0.79
    al
    0.79
    ;
    0.79
    POSITIVE LOGITS
     skeletons
    0.99
    ల
    0.97
     corpses
    0.91
    ’
    0.87
     forks
    0.86
     skulls
    0.83
    హ
    0.83
     skeleton
    0.79
     shelters
    0.78
     hogy
    0.78
    Activations Density 0.007%

    No Known Activations