© 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. 98970
    Prev
    Next
    INDEX
    Explanations

    names and labels

    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
    filt
    -0.75
    法则
    -0.71
     inférieure
    -0.69
    rifle
    -0.69
    伊藤
    -0.68
     liées
    -0.67
    ándonos
    -0.67
     Forst
    -0.66
    juste
    -0.66
     twelfth
    -0.66
    POSITIVE LOGITS
    Walter
    0.93
     Walter
    0.88
     Carolyn
    0.82
    超
    0.80
     Jaime
    0.73
    十
    0.73
    千
    0.72
    twenty
    0.71
    东
    0.71
    池
    0.71
    Activations Density 0.334%

    No Known Activations