© 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. 62401
    Prev
    Next
    INDEX
    Explanations

    URLs including github

    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
    getMenuInflater
    -0.81
    ){}
    -0.80
     miejsco
    -0.77
    性别
    -0.77
    älj
    -0.77
    ான்
    -0.77
    jointed
    -0.75
     manquer
    -0.73
    attached
    -0.73
     conversación
    -0.73
    POSITIVE LOGITS
    git
    0.88
     git
    0.85
     Maury
    0.84
    ddress
    0.79
     Assess
    0.77
    སྐ
    0.72
     Reporters
    0.72
    Mirrors
    0.71
    ərb
    0.71
     subtree
    0.71
    Activations Density 0.051%

    No Known Activations