© 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. 78098
    Prev
    Next
    INDEX
    Explanations

    numerical durations and parts

    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
     Pesticides
    -0.95
     gevo
    -0.87
    gados
    -0.77
    ługa
    -0.77
     *-
    -0.75
     denounced
    -0.75
     じゃ
    -0.74
     tiên
    -0.73
     Hann
    -0.73
    vemos
    -0.73
    POSITIVE LOGITS
     week
    1.19
     module
    1.02
     hour
    0.95
     step
    0.95
     simple
    0.93
     Part
    0.93
     Module
    0.93
     Week
    0.91
     part
    0.86
     Step
    0.86
    Activations Density 0.040%

    No Known Activations