© 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. 48569
    Prev
    Next
    INDEX
    Explanations

    zone number

    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
    findBy
    -0.81
    By
    -0.81
    getInfo
    -0.79
     simmer
    -0.76
     findBy
    -0.74
     By
    -0.73
    arResult
    -0.72
    pagnole
    -0.72
     nephew
    -0.71
    Jennifer
    -0.71
    POSITIVE LOGITS
     Eighteen
    0.73
     acute
    0.69
    十八
    0.69
    ۱۸
    0.69
     Oak
    0.67
    <0xE7>
    0.67
     cuarta
    0.65
     Organic
    0.65
    iar
    0.64
    急性
    0.64
    Activations Density 0.411%

    No Known Activations