© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 92970
    Prev
    Next
    INDEX
    Explanations

    method calls and code execution

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

    The neuron fires on method‐name tokens in function or procedure definitions (identifiers immediately followed by “()”).

    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
    蛱
    -1.46
     Aceite
    -1.43
     imprensa
    -1.38
    lxt
    -1.32
     noiva
    -1.28
     estadia
    -1.26
    relatively
    -1.23
    鐃
    -1.23
    dans
    -1.22
    zaSy
    -1.20
    POSITIVE LOGITS
    !
    1.43
    ()
    1.43
     after
    1.37
     increases
    1.27
     gets
    1.25
     antiquated
    1.22
     suggests
    1.20
    (
    1.20
     takes
    1.18
     atau
    1.18
    Activations Density 0.001%

    No Known Activations