© 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. 195619
    Prev
    Next
    INDEX
    Explanations

    need for periods

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

    special characters and symbols

    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
     ammunition
    0.44
     ornament
    0.44
     寸
    0.42
    メント
    0.42
     ottoman
    0.40
     pepperoni
    0.40
     って
    0.39
    雱
    0.39
    LIKE
    0.39
    フラワー
    0.39
    POSITIVE LOGITS
     হাজির
    0.46
     احتمال
    0.44
     വളരെ
    0.43
     Semantic
    0.43
     Perhaps
    0.43
     فهر
    0.42
     σχετικά
    0.42
     Voices
    0.42
     فترة
    0.42
     конкурса
    0.41
    Activations Density 0.003%

    No Known Activations