© 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. 48536
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

    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
    DBC
    -0.63
    /\
    -0.62
    Lap
    -0.62
    pastebin
    -0.60
    Selenium
    -0.60
     刘
    -0.60
     함
    -0.60
    ohistochemistry
    -0.59
    Underline
    -0.57
    Gate
    -0.57
    POSITIVE LOGITS
     Schofield
    0.74
     spatula
    0.73
    zee
    0.69
     обита
    0.69
    zia
    0.68
    rativa
    0.67
    唯有
    0.67
     могли
    0.66
    carbonate
    0.66
     NON
    0.66
    Activations Density 0.088%

    No Known Activations