© 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. 30877
    Prev
    Next
    INDEX
    Explanations

    first edition

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

    editions, first editions, signed copies

    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
    几年
    0.41
     SALE
    0.41
     مشتری
    0.41
     pyridine
    0.40
    腮
    0.40
    sup
    0.40
     payoff
    0.40
    中标
    0.40
     supere
    0.39
     Sup
    0.39
    POSITIVE LOGITS
    icheskij
    0.41
     populist
    0.40
     absolv
    0.40
    //!
    0.39
    ავი
    0.39
    getToken
    0.39
     काबू
    0.39
     />,
    0.39
    avni
    0.39
    ()),
    0.38
    Activations Density 0.019%

    No Known Activations