© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57300
    Prev
    Next
    INDEX
    Explanations

    script and link 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
    ikti
    -0.97
    ikko
    -0.95
    JoinTable
    -0.94
     tocó
    -0.93
    aliere
    -0.89
     Ferns
    -0.88
    АО
    -0.88
     laço
    -0.87
     voluto
    -0.85
    ஞ
    -0.84
    POSITIVE LOGITS
    script
    1.39
    link
    1.20
     link
    1.17
     script
    0.96
    Scripts
    0.86
     links
    0.84
     scripts
    0.81
    scripts
    0.80
     LINK
    0.80
    drops
    0.78
    Activations Density 0.020%

    No Known Activations