© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    finding visually similar

    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
    <unused250>
    0.57
    <unused2032>
    0.56
    椑
    0.54
    তাহাকে
    0.54
    <unused659>
    0.52
     GoName
    0.51
    <unused451>
    0.51
     Chayin
    0.50
     juf
    0.50
     dajj
    0.50
    POSITIVE LOGITS
    0.73
    ↵↵
    0.46
    ;
    0.46
    <strong>
    0.43
    さい
    0.43
    正
    0.42
    真
    0.41
    ...
    0.41
    Contact
    0.39
    С
    0.39
    Activations Density 0.000%

    No Known Activations