© 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. 10-GEMMASCOPE-RES-131K
    7. 100784
    Prev
    Next
    INDEX
    Explanations

    Apache 2.0 license headers

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

    references to software foundations, organizations, and proper names in code (like "Microsoft", "Apache", "ASF", "Contributors", and technical identifiers).

    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
     чёрный
    -1.08
    0
    -1.05
    』(
    -1.02
     we
    -0.98
     estampado
    -0.97
    visibility
    -0.95
     INVESTIG
    -0.95
     breadcrumbs
    -0.93
    cyjny
    -0.93
     levert
    -0.93
    POSITIVE LOGITS
    %">
    1.24
     जबकि
    1.23
     dejando
    1.20
    ()){
    1.18
    uspiel
    1.15
    </b>
    1.15
    huriyet
    1.15
    asem
    1.13
    %;">
    1.13
     cỡ
    1.11
    Activations Density 0.039%

    No Known Activations