© 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. 184826
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, or specific items

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

    printf functions

    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
    बंधित
    0.45
    <0xB2>
    0.44
     раду
    0.44
     Newtown
    0.44
     Registry
    0.43
    miş
    0.43
     ʼ
    0.43
     Hartford
    0.42
     ны
    0.42
    éricas
    0.42
    POSITIVE LOGITS
    NOMBRE
    0.46
    질
    0.43
     materias
    0.43
    비스
    0.43
    삭
    0.43
     sujets
    0.42
    )}(\
    0.41
    SLE
    0.41
    至于
    0.41
     costumbre
    0.41
    Activations Density 0.000%

    No Known Activations