© 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. 16465
    Prev
    Next
    INDEX
    Explanations

    time and answer clarification

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

    calculations and formulas

    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
    ю
    0.52
    ي
    0.47
    Р
    0.47
    app
    0.47
    يق
    0.40
    联
    0.40
    ).
    0.40
    Б
    0.39
    يرة
    0.39
    ريقة
    0.39
    POSITIVE LOGITS
     parsing
    0.55
     χώ
    0.47
     nejen
    0.46
    นู
    0.45
     meiosis
    0.42
    Parsing
    0.42
     biodegradation
    0.42
    いくつか
    0.41
     timedelta
    0.41
     composición
    0.41
    Activations Density 0.000%

    No Known Activations