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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60856
    Prev
    Next
    INDEX
    Explanations

    stock tickers and code separators

    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
    nerable
    -0.75
     prosec
    -0.75
     VHS
    -0.73
    блема
    -0.71
    poved
    -0.70
     смысле
    -0.68
    Numbers
    -0.68
    ناول
    -0.68
    ==""){
    -0.68
    🟧
    -0.68
    POSITIVE LOGITS
    couverte
    0.81
     jule
    0.79
     positifs
    0.79
    chloric
    0.77
    ANGAN
    0.75
    angan
    0.75
    ne
    0.75
     Dissolved
    0.74
    찐
    0.74
    acne
    0.73
    Activations Density 0.061%

    No Known Activations