© 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. 174044
    Prev
    Next
    INDEX
    Explanations

    location descriptions

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

    "may be", "than", "increases", "secret from", "as it's", "Cover Letter"

    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
    дри
    0.59
    brev
    0.58
    TEN
    0.51
    ف
    0.51
    NATIONAL
    0.50
    БА
    0.50
    ap
    0.49
    THERE
    0.49
    Dre
    0.48
    NE
    0.48
    POSITIVE LOGITS
     Hodge
    0.50
     aquifer
    0.45
     vyr
    0.45
     Pah
    0.45
     Roanoke
    0.45
    ̥
    0.44
     hiatus
    0.44
    lacian
    0.44
     Kei
    0.44
     reson
    0.44
    Activations Density 0.000%

    No Known Activations