© 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. 36904
    Prev
    Next
    INDEX
    Explanations

    introductory phrases

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

    Physical development and appearance

    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
    _
    0.52
     these
    0.50
    my
    0.49
     came
    0.49
    ",
    0.49
    시
    0.49
     Thị
    0.48
     다음에
    0.47
    गंगा
    0.46
     to
    0.45
    POSITIVE LOGITS
     хотим
    0.52
    られます
    0.48
     retângulo
    0.48
     хочется
    0.48
    ஷ்ய
    0.47
    ָד
    0.46
    冑
    0.44
     স্বাধীনতা
    0.43
    ガー
    0.43
    reflectionMap
    0.42
    Activations Density 0.000%

    No Known Activations