© 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. 41778
    Prev
    Next
    INDEX
    Explanations

    predicting future actions

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

    to verb

    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
    d
    0.74
    زاده
    0.71
    a
    0.69
    ্বের
    0.68
    ON
    0.68
    وت
    0.67
    গোষ্ঠ
    0.67
    он
    0.66
    C
    0.64
    வல்
    0.64
    POSITIVE LOGITS
    .
    0.84
    ’
    0.77
    li
    0.77
    ى
    0.71
     be
    0.67
    ly
    0.67
     شما
    0.67
     numeros
    0.67
    to
    0.64
    ust
    0.63
    Activations Density 0.054%

    No Known Activations