© 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. 63056
    Prev
    Next
    INDEX
    Explanations

    common sentence starters

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

    calculation context

    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
    imely
    0.48
    उन्होंने
    0.47
    চেতন
    0.45
    Majority
    0.45
     சூழ்
    0.43
     policymakers
    0.42
     তারা
    0.42
    𐰣
    0.42
     instituciones
    0.41
     unwa
    0.41
    POSITIVE LOGITS
     wiki
    0.49
     керек
    0.48
     AND
    0.44
    增加了
    0.44
     perhaps
    0.44
     logon
    0.44
     يزيد
    0.43
     increases
    0.43
     高
    0.43
     footprint
    0.42
    Activations Density 0.000%

    No Known Activations