© 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. 22-GEMMASCOPE-RES-131K
    7. 34638
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

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

    The neuron fires on the names and types of parameters in function or method signatures (the comma-separated identifiers and types inside the parentheses of declarations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     every
    -1.44
     now
    -1.41
     not
    -1.41
     because
    -1.38
     more
    -1.36
     after
    -1.36
     just
    -1.34
     almost
    -1.31
     first
    -1.31
     considerably
    -1.30
    POSITIVE LOGITS
     trám
    1.57
    might
    1.36
    ⚌
    1.26
     intrigu
    1.25
     wondrous
    1.24
     espesor
    1.22
    inerario
    1.21
     startling
    1.20
     ayur
    1.20
     prendre
    1.19
    Activations Density 0.006%

    No Known Activations