© 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. 166619
    Prev
    Next
    INDEX
    Explanations

    services and guarantees

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

    coding characters and metrics

    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
    दि
    0.50
    シ
    0.48
    Scient
    0.47
    in
    0.47
    i
    0.47
    inflammation
    0.46
    文
    0.46
    メ
    0.45
    キ
    0.45
    ιδ
    0.45
    POSITIVE LOGITS
     modernized
    0.53
     Isis
    0.52
     problemat
    0.51
     Gertrude
    0.47
     Mozilla
    0.47
     Freddie
    0.47
     Bandar
    0.47
     постоянно
    0.46
     sexu
    0.46
     squirrels
    0.46
    Activations Density 0.001%

    No Known Activations