© 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-65K
    7. 45712
    Prev
    Next
    INDEX
    Explanations

    html, css, and javascript

    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_65k_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
    の両
    0.71
    larını
    0.63
    ları
    0.62
    ’
    0.62
    '
    0.61
    ,
    0.60
    می
    0.58
    ,'
    0.56
    の部分
    0.56
    larının
    0.56
    POSITIVE LOGITS
     Html
    0.63
    the
    0.63
     enige
    0.62
     Avec
    0.58
    ul
    0.57
     Bucs
    0.57
    ل
    0.57
     outlying
    0.56
    ர்
    0.55
    溸
    0.55
    Activations Density 0.030%

    No Known Activations