© 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. 118016
    Prev
    Next
    INDEX
    Explanations

    rules and requirements

    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
    ∕
    -0.93
     Maia
    -0.89
    ("./
    -0.82
    enddo
    -0.81
    ļ
    -0.78
    hlí
    -0.77
    flix
    -0.75
    Blockly
    -0.75
    melon
    -0.74
     identical
    -0.73
    POSITIVE LOGITS
     rules
    1.20
     Rule
    0.91
     Rules
    0.88
     rule
    0.86
     [
    0.85
    パスタ
    0.82
     geralmente
    0.82
     regole
    0.81
    rules
    0.78
    RULE
    0.77
    Activations Density 0.003%

    No Known Activations