© 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. 8139
    Prev
    Next
    INDEX
    Explanations

    dedicate, what, room, send, Girls

    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
    erns
    0.52
    <0x86>
    0.48
    魍
    0.48
     Castel
    0.45
    长安
    0.44
    దన
    0.44
    建筑
    0.44
    内置
    0.43
     образа
    0.43
    ias
    0.43
    POSITIVE LOGITS
    োগান
    0.41
    uatan
    0.39
    dictionary
    0.38
     Receivable
    0.38
    unuh
    0.38
    da
    0.38
    ]]></
    0.38
     Ocean
    0.37
     ister
    0.37
     gev
    0.37
    Activations Density 0.000%

    No Known Activations