© 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. 73014
    Prev
    Next
    INDEX
    Explanations

    patent claims

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

    ranges like low under

    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
    验
    0.50
    籿
    0.44
    柅
    0.44
    纭
    0.43
     supp
    0.43
     FORT
    0.42
    ни
    0.42
    公安
    0.42
     fort
    0.41
     recur
    0.41
    POSITIVE LOGITS
     Bennett
    0.46
    odeled
    0.44
     मजाक
    0.43
    jela
    0.43
    oksi
    0.43
    jogador
    0.42
    $
    0.42
    blogspot
    0.42
    olato
    0.42
    essoa
    0.41
    Activations Density 0.003%

    No Known Activations