© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77196
    Prev
    Next
    INDEX
    Explanations

    award nominations and ceremonies

    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
    チョウ
    -0.81
     רק
    -0.79
     Yup
    -0.76
     squat
    -0.75
     Carn
    -0.75
    不应该
    -0.74
     PML
    -0.74
    fai
    -0.73
    カド
    -0.73
     JI
    -0.73
    POSITIVE LOGITS
     Choice
    0.81
     Gotham
    0.80
     Satellite
    0.76
     critic
    0.75
     Association
    0.75
    > 
    0.73
     Australian
    0.73
    KeySpec
    0.73
    英国
    0.72
    haft
    0.71
    Activations Density 0.026%

    No Known Activations