© 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. 25445
    Prev
    Next
    INDEX
    Explanations

    rub them

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

    code, technical terms, identifiers

    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
     बदनाम
    0.46
    ف
    0.46
     Shil
    0.44
     Familien
    0.44
     scanty
    0.44
     Midi
    0.43
    කාර
    0.43
    کیل
    0.42
     cursing
    0.42
    ത
    0.42
    POSITIVE LOGITS
    📎
    0.45
     источник
    0.44
     源
    0.43
    🌈
    0.41
    面向
    0.41
    🔗
    0.39
    🐉
    0.39
    逺
    0.39
     сер
    0.39
    ERCE
    0.39
    Activations Density 0.000%

    No Known Activations