© 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. 100550
    Prev
    Next
    INDEX
    Explanations

    interface type definitions

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

    the keyword "interface" in programming code, particularly in Go and Java type declarations.

    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
    shimano
    -1.90
    :'#
    -1.74
    掮
    -1.71
    Fart
    -1.70
     شیپور
    -1.66
    局面
    -1.66
    figurine
    -1.65
     giyim
    -1.63
    Manufact
    -1.63
     graciosas
    -1.62
    POSITIVE LOGITS
    .
    2.66
    </h3>
    2.20
    and
    1.68
     ещё
    1.66
    2
    1.60
    </strong>
    1.59
     soja
    1.55
    踊
    1.50
    Math
    1.48
    Damn
    1.48
    Activations Density 0.002%

    No Known Activations