© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49079
    Prev
    Next
    INDEX
    Explanations

    Southern Illinois locations

    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
    hado
    -0.77
    Comput
    -0.76
    comp
    -0.75
    лій
    -0.73
     правило
    -0.72
    tritts
    -0.72
    cfg
    -0.72
     turi
    -0.71
    yun
    -0.70
    CFG
    -0.70
    POSITIVE LOGITS
     Saline
    0.86
    bondale
    0.84
     Egyptian
    0.82
     Evansville
    0.82
    siu
    0.80
     Illinois
    0.80
    StringVar
    0.80
    porsche
    0.79
    Egyptian
    0.77
     SI
    0.75
    Activations Density 0.023%

    No Known Activations