© 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. 111936
    Prev
    Next
    INDEX
    Explanations

    go cgo and build tags

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

    build directives and cgo compiler instructions in Go source code comments.

    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
     gangen
    -1.63
    hiculo
    -1.61
    sich
    -1.53
     trener
    -1.52
    емость
    -1.50
     obiet
    -1.49
    奩
    -1.48
     aussit
    -1.48
     vitesses
    -1.47
    tabolism
    -1.46
    POSITIVE LOGITS
     
    1.51
    ↵
    1.48
     it
    1.41
    What
    1.34
     would
    1.33
    </strong>
    1.31
     one
    1.26
     there
    1.25
    It
    1.24
    </h4>
    1.23
    Activations Density 0.020%

    No Known Activations