© 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. 41-GEMMASCOPE-2-RES-262K
    7. 34909
    Prev
    Next
    INDEX
    Explanations

    legal documents and forms

    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_all/layer_41_width_262k_l0_big
    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
     espirit
    0.45
     JUSTICE
    0.42
     dentist
    0.42
    敍
    0.41
     lư
    0.41
    ))^
    0.40
    ).__
    0.40
    Justice
    0.40
     expedit
    0.39
    锯
    0.39
    POSITIVE LOGITS
     forms
    0.55
     Analysis
    0.47
     Forms
    0.47
     analysed
    0.46
     clauses
    0.46
    forms
    0.46
     analysis
    0.45
     formes
    0.44
     form
    0.43
    Analysis
    0.42
    Activations Density 0.001%

    No Known Activations