© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85957
    Prev
    Next
    INDEX
    Explanations

    structure markers

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

    describing and completing concepts

    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
    o
    0.54
    ться
    0.52
     at
    0.51
    <h1>
    0.50
     <
    0.49
    首页
    0.48
    Please
    0.48
    Video
    0.47
    ession
    0.47
    >
    0.46
    POSITIVE LOGITS
    いた
    0.64
    abhavena
    0.61
    スペイン
    0.59
     obeyed
    0.57
     severed
    0.57
    dır
    0.56
     کە
    0.56
    스
    0.56
    itamento
    0.55
    tDBOutput
    0.54
    Activations Density 0.051%

    No Known Activations