© 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. 10-GEMMASCOPE-RES-131K
    7. 100320
    Prev
    Next
    INDEX
    Explanations

    android layout styleable

    np_acts-logits-general · gemini-2.5-flash-lite

    periods (dots) that follow identifiers in code, indicating member access or namespace/package separators.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -2.03
     for
    -2.00
     ONLY
    -1.95
     first
    -1.86
     intricate
    -1.80
     with
    -1.77
     by
    -1.66
     massive
    -1.66
     дуже
    -1.63
     resolute
    -1.63
    POSITIVE LOGITS
    perhaps
    1.84
     verschillende
    1.72
    ändigen
    1.69
    ↵
    1.60
     confezione
    1.55
    probably
    1.52
     largely
    1.51
     diferite
    1.50
    possibly
    1.49
     neces
    1.47
    Activations Density 0.001%

    No Known Activations