© 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. 117382
    Prev
    Next
    INDEX
    Explanations

    medium, programming, job postings

    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
     cosmology
    -0.73
    hasia
    -0.72
    aide
    -0.69
    &&\
    -0.67
     знать
    -0.67
     работать
    -0.67
    roveň
    -0.67
     terceira
    -0.67
    亻
    -0.66
    Jakob
    -0.66
    POSITIVE LOGITS
     Philadelphia
    0.72
     QB
    0.71
    site
    0.70
    χή
    0.69
    uyor
    0.67
    నా
    0.67
    rying
    0.67
     Irish
    0.66
     IO
    0.66
    conn
    0.65
    Activations Density 0.045%

    No Known Activations