© 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. 57030
    Prev
    Next
    INDEX
    Explanations

    spring, react, spark, angular

    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
    сах
    -0.88
    GARD
    -0.68
    姑娘
    -0.68
     Yup
    -0.64
     anvil
    -0.63
    🅘
    -0.63
    青岛
    -0.63
    وفاته
    -0.63
     titoli
    -0.63
     наде
    -0.62
    POSITIVE LOGITS
    launcher
    0.77
    SEMICOLON
    0.77
     intelig
    0.74
     coleg
    0.74
    urum
    0.73
     Buf
    0.73
     dikatakan
    0.72
     tabela
    0.71
     TAK
    0.71
    randir
    0.71
    Activations Density 0.016%

    No Known Activations