© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57860
    Prev
    Next
    INDEX
    Explanations

    Avon, Canton, Farmington

    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
     உ
    -0.78
     Що
    -0.74
     Ministère
    -0.73
    🛋
    -0.72
     Aussie
    -0.71
     effusion
    -0.71
    勁
    -0.71
     legume
    -0.70
     pelvis
    -0.70
    зион
    -0.69
    POSITIVE LOGITS
     Avon
    1.31
    Avon
    1.24
     avon
    0.96
    avon
    0.89
    avons
    0.87
    lea
    0.80
    Gli
    0.79
     Campaign
    0.76
     döne
    0.73
    ДА
    0.73
    Activations Density 0.009%

    No Known Activations