© 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. 103013
    Prev
    Next
    INDEX
    Explanations

    rightsassemblysegregation

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

    concepts, drugs, mutations, placement

    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
     via
    0.46
     tow
    0.44
     dirige
    0.43
    연
    0.42
     bodily
    0.42
    ोज़
    0.42
     directing
    0.40
     nuovi
    0.40
     갈
    0.40
    节目
    0.40
    POSITIVE LOGITS
     教育
    0.45
     ብዙውን
    0.44
    <unused85>
    0.43
     الكثير
    0.42
     ойношот
    0.42
     అనేది
    0.41
     政府
    0.41
     Иногда
    0.41
     жар
    0.40
     کبھی
    0.40
    Activations Density 0.000%

    No Known Activations