© 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. 199505
    Prev
    Next
    INDEX
    Explanations

    description or specification

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

    generally accepted facts and trends

    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
    -
    0.62
    antis
    0.49
    imax
    0.49
    usso
    0.47
    prise
    0.47
    prises
    0.47
    umar
    0.47
    ajal
    0.47
    ub
    0.46
    mec
    0.46
    POSITIVE LOGITS
     Arkadaşlar
    0.54
     Yemek
    0.48
     刘
    0.47
     तोड़ने
    0.47
     သူမ
    0.47
     Từ
    0.46
     Kamu
    0.46
     फॉर
    0.45
     Projek
    0.45
     Parsing
    0.45
    Activations Density 0.001%

    No Known Activations