© 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. 82848
    Prev
    Next
    INDEX
    Explanations

    specific actions and items

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

    data attributes and possibilities

    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
    Negative Logits
    al
    0.55
    ab
    0.48
    es
    0.48
    e
    0.47
     haven
    0.45
    i
    0.45
    ol
    0.45
     Church
    0.44
     discouraged
    0.44
    ant
    0.44
    POSITIVE LOGITS
    thapi
    0.56
     ))->
    0.56
     мае
    0.55
    midrule
    0.54
    ᆞ
    0.54
    눠
    0.48
    assara
    0.48
     লাহ
    0.48
     onclick
    0.47
     দেখিল
    0.46
    Activations Density 0.000%

    No Known Activations