© 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. 133115
    Prev
    Next
    INDEX
    Explanations

    Microsoft, cheese, discussion, short

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

    payloads, snow, customers, capital

    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
    同
    0.53
    데일리
    0.49
    aupt
    0.48
    ocia
    0.45
    ynyt
    0.45
    果
    0.44
    Cole
    0.44
    allas
    0.44
    fnamefont
    0.44
    〔
    0.44
    POSITIVE LOGITS
     ?></
    0.43
    >©
    0.43
    ынша
    0.43
     ការ
    0.43
     SMB
    0.42
    прав
    0.42
    ColorLegend
    0.42
    UILLER
    0.41
    可以让
    0.41
    ковка
    0.41
    Activations Density 0.002%

    No Known Activations