© 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. 32032
    Prev
    Next
    INDEX
    Explanations

    script letters and greek symbols

    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
    𝒢
    -0.82
     epa
    -0.77
     paula
    -0.75
    𝒦
    -0.74
    Commons
    -0.74
     VISA
    -0.73
    ’
    -0.73
     tzu
    -0.72
    racks
    -0.72
    шных
    -0.72
    POSITIVE LOGITS
    mathcal
    1.96
     cal
    1.53
    cal
    1.44
    Cal
    1.30
     Cal
    1.23
     ${\
    1.22
    mathscr
    1.22
     Cali
    1.22
     calli
    1.19
     $\
    1.14
    Activations Density 0.060%

    No Known Activations