© 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. 37747
    Prev
    Next
    INDEX
    Explanations

    code navigation and compilation

    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
    アド
    -0.76
    开车
    -0.72
    ANALYSIS
    -0.70
    dv
    -0.69
    ћи
    -0.68
    HostException
    -0.64
     adipis
    -0.64
    Duff
    -0.63
     Projections
    -0.63
     aren
    -0.63
    POSITIVE LOGITS
    ority
    0.90
     lys
    0.81
     repair
    0.79
     jär
    0.74
    +]
    0.73
     общения
    0.73
     Feria
    0.72
    grana
    0.72
     Implementing
    0.71
    fitted
    0.71
    Activations Density 0.019%

    No Known Activations