© 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. 47184
    Prev
    Next
    INDEX
    Explanations

    documentation structure or code blocks

    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
    Negative Logits
    lock
    -0.69
    如下图
    -0.69
     وات
    -0.67
    vap
    -0.67
     Paolo
    -0.66
     VEN
    -0.64
     gasoline
    -0.63
    vp
    -0.63
     capitalize
    -0.63
    like
    -0.63
    POSITIVE LOGITS
     mathématiques
    0.71
    regar
    0.71
     Zona
    0.69
    }}_
    0.69
    زيز
    0.69
    本書
    0.68
     клей
    0.68
    FactoryBean
    0.68
     Decorating
    0.68
     книг
    0.67
    Activations Density 0.091%

    No Known Activations