© 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. 112814
    Prev
    Next
    INDEX
    Explanations

    THIS question, Awareness Program

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

    continuation or elaboration

    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
    h
    0.55
     owning
    0.49
     UG
    0.46
     specializing
    0.46
     Nürnberg
    0.44
     collaborating
    0.44
     Molina
    0.44
     bầu
    0.43
     mineralization
    0.43
    ug
    0.42
    POSITIVE LOGITS
    他不
    0.51
    อร์
    0.50
    ⛹
    0.49
    Json
    0.49
     Соответ
    0.49
    ণিত
    0.46
    마다
    0.45
    iquement
    0.45
    許
    0.45
     టెస్
    0.44
    Activations Density 0.000%

    No Known Activations