© 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. 63690
    Prev
    Next
    INDEX
    Explanations

    Penn State University

    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
     tě
    -0.78
    ኣ
    -0.73
     prenatal
    -0.73
    wam
    -0.72
    OKU
    -0.70
    ulaski
    -0.69
    的第一
    -0.68
    Meski
    -0.68
     cuna
    -0.68
    isierte
    -0.68
    POSITIVE LOGITS
    psu
    1.20
     Penn
    1.18
     PSU
    1.09
    Penn
    1.05
    fonte
    1.00
    PSU
    1.00
     Lion
    0.93
     Pater
    0.90
     Schre
    0.88
     Mifflin
    0.87
    Activations Density 0.026%

    No Known Activations