© 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. 74137
    Prev
    Next
    INDEX
    Explanations

    run out after

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

    AI canned refusal disclaimer

    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
    Unh
    0.48
    盛
    0.46
    腹
    0.45
    呔
    0.44
    شاه
    0.44
    核心
    0.43
    }\}
    0.43
    머니
    0.43
    粤
    0.42
    flashdata
    0.41
    POSITIVE LOGITS
     that
    0.50
     some
    0.48
     Era
    0.47
     Day
    0.47
     noen
    0.47
     aaa
    0.47
     clogging
    0.46
     new
    0.46
     joka
    0.46
     uber
    0.46
    Activations Density 0.002%

    No Known Activations