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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64873
    Prev
    Next
    INDEX
    Explanations

    javascript and script tags

    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
     sangre
    -0.77
    يانة
    -0.73
     aeroplane
    -0.71
     waterway
    -0.68
     salsa
    -0.68
    qld
    -0.66
    Wrath
    -0.66
     verbe
    -0.65
    Lamin
    -0.65
     caregiver
    -0.65
    POSITIVE LOGITS
     script
    3.55
     scripts
    3.28
    script
    3.28
    Script
    2.84
     Script
    2.59
    scripts
    2.59
    SCRIPT
    2.58
    Scripts
    2.52
     SCRIPT
    2.42
     Scripts
    2.39
    Activations Density 0.193%

    No Known Activations