© 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. 79255
    Prev
    Next
    INDEX
    Explanations

    functions and management

    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
    cepteur
    -0.81
     ног
    -0.78
    partite
    -0.75
     may
    -0.73
    فات
    -0.73
    andai
    -0.71
    entrega
    -0.70
    ẩy
    -0.69
     constructs
    -0.69
     stared
    -0.68
    POSITIVE LOGITS
    Fay
    1.10
     Fay
    1.05
     managerial
    0.88
    llano
    0.87
     Functions
    0.81
    经营
    0.81
     Mindanao
    0.80
     LOWER
    0.80
    Henri
    0.80
    Functions
    0.79
    Activations Density 0.011%

    No Known Activations