© 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. 10812
    Prev
    Next
    INDEX
    Explanations

    rates, statistics, simple

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

    listing items or descriptions

    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
    ata
    0.58
    ite
    0.48
    aya
    0.47
    aila
    0.47
    iend
    0.47
    flexible
    0.47
    AYA
    0.46
    a
    0.46
    tect
    0.46
    enter
    0.46
    POSITIVE LOGITS
     простых
    0.46
    呼び
    0.46
    算
    0.44
     semplici
    0.43
     przyp
    0.43
     Rate
    0.43
    野
    0.43
    率は
    0.42
     représentation
    0.42
     stati
    0.42
    Activations Density 0.000%

    No Known Activations