© 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. 67253
    Prev
    Next
    INDEX
    Explanations

    keyword followed by common phrase

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

    explaining terms and formats

    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
    ೊಳ
    0.52
    дни
    0.47
    органи
    0.46
     thèse
    0.46
    酔
    0.45
    печат
    0.45
    꾿
    0.45
    몸
    0.45
    롱
    0.44
    猟
    0.44
    POSITIVE LOGITS
    _
    0.54
    Lt
    0.52
    Sa
    0.47
    Super
    0.45
    Min
    0.44
    )))))
    0.44
    \
    0.44
     spices
    0.43
    Grade
    0.42
    Sh
    0.42
    Activations Density 0.000%

    No Known Activations