© 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. 31448
    Prev
    Next
    INDEX
    Explanations

    legal documents and code

    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
    hata
    -0.71
     overwritten
    -0.66
    hoid
    -0.66
    localtime
    -0.65
    崧
    -0.64
     coff
    -0.64
    tér
    -0.63
    ждается
    -0.63
    MARTIN
    -0.63
     dlou
    -0.63
    POSITIVE LOGITS
    addHeader
    0.73
    ✿
    0.70
     workload
    0.69
     workloads
    0.69
     oscar
    0.68
    mira
    0.67
    дьми
    0.67
     rendering
    0.67
     Henrietta
    0.67
     concur
    0.66
    Activations Density 0.050%

    No Known Activations