© 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. 3275
    Prev
    Next
    INDEX
    Explanations

    programming library imports

    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
     sobra
    -0.82
    해서
    -0.75
     egyszerű
    -0.73
     parameterized
    -0.73
     decorar
    -0.73
    zeichnung
    -0.71
    ("{
    -0.70
     kitchenette
    -0.69
     nią
    -0.69
    MACRO
    -0.69
    POSITIVE LOGITS
     scientific
    1.00
    Sci
    0.96
     Sci
    0.94
     syscall
    0.93
     Accord
    0.93
     sci
    0.92
     scientists
    0.91
     Jama
    0.90
     Math
    0.89
     OpenCV
    0.88
    Activations Density 0.081%

    No Known Activations