© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109572
    Prev
    Next
    INDEX
    Explanations

    min.js, .css, missing, login, findings

    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
     barnen
    -0.76
     dioxide
    -0.72
     apoy
    -0.71
     общего
    -0.70
    np
    -0.69
    sass
    -0.69
    ational
    -0.69
     Mark
    -0.68
     کافی
    -0.68
     лъ
    -0.68
    POSITIVE LOGITS
    bundle
    0.95
     parallels
    0.82
     diagnos
    0.81
     amalgamation
    0.81
     bundles
    0.79
    成品
    0.79
     Bundle
    0.78
    Bundle
    0.78
     §.
    0.77
     ardu
    0.77
    Activations Density 0.020%

    No Known Activations