© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30257
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uel
    -0.76
    Xiv
    -0.76
     pranzo
    -0.76
    ={\
    -0.75
     اصول
    -0.74
     σελ
    -0.71
    Sal
    -0.71
    OLOG
    -0.70
     Newt
    -0.70
     Thousands
    -0.69
    POSITIVE LOGITS
    Aer
    0.76
    unsaturated
    0.73
    ènements
    0.69
    kasa
    0.69
    妈
    0.68
    enzyme
    0.68
     meant
    0.68
    忍者
    0.68
    amphetamine
    0.68
    mothers
    0.67
    Activations Density 0.036%

    No Known Activations