© 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. 89845
    Prev
    Next
    INDEX
    Explanations

    ToolStrip and Menu elements

    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
    getMessage
    -0.79
    letín
    -0.78
    懷
    -0.77
    Indo
    -0.76
     cuaderno
    -0.75
     Hort
    -0.73
    Referencie
    -0.72
    Freight
    -0.71
    setFrame
    -0.69
     selectors
    -0.69
    POSITIVE LOGITS
    ToolStrip
    2.09
     Tool
    1.45
     tool
    1.38
    tool
    1.30
    Strip
    1.27
     TS
    1.20
    strip
    1.20
    toolStrip
    1.16
     Strip
    1.16
     toolStrip
    1.13
    Activations Density 0.012%

    No Known Activations