© 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. 152346
    Prev
    Next
    INDEX
    Explanations

    services, Delhi, completion

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

    numerical list items and definitions

    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
     importer
    0.44
     alanı
    0.44
    ውስ
    0.44
    زى
    0.43
     hält
    0.43
     gard
    0.43
    <0xDB>
    0.42
     Masa
    0.42
     abort
    0.42
     getCurrent
    0.42
    POSITIVE LOGITS
    ヨン
    0.55
    otemporal
    0.54
    లేని
    0.47
    gr
    0.47
    formas
    0.46
    har
    0.46
    pros
    0.45
    隠
    0.45
    patterns
    0.45
    pora
    0.45
    Activations Density 0.000%

    No Known Activations