© 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. 113259
    Prev
    Next
    INDEX
    Explanations

    javascript function calls

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

    method calls or function invocations in programming code, particularly those that initiate actions like API requests, file operations, or data retrieval.

    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
     also
    -1.66
     unless
    -1.56
     they
    -1.34
     cuando
    -1.34
    也有
    -1.33
    いても
    -1.30
     alſo
    -1.27
     same
    -1.27
     when
    -1.21
    もある
    -1.20
    POSITIVE LOGITS
     hảo
    1.44
     accompagner
    1.36
     Isten
    1.33
     srdce
    1.32
    Allah
    1.28
    rát
    1.27
    Winner
    1.26
    怍
    1.26
    leicht
    1.26
    ěř
    1.23
    Activations Density 0.024%

    No Known Activations