© 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. 160428
    Prev
    Next
    INDEX
    Explanations

    foreign currency or numbers

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

    words of affirmation

    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
     пур
    0.46
    DAG
    0.43
    ש
    0.43
    )")
    0.43
     Вер
    0.42
     পরিচয়
    0.41
    IN
    0.41
    gahan
    0.41
    AY
    0.40
    ):["
    0.40
    POSITIVE LOGITS
     deux
    0.59
     doua
    0.56
    👕
    0.54
     Economía
    0.50
     laquelle
    0.50
     două
    0.50
     temporada
    0.49
    يطان
    0.49
     nieuwe
    0.47
    يدي
    0.47
    Activations Density 0.001%

    No Known Activations