© 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. 38316
    Prev
    Next
    INDEX
    Explanations

    File operations

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

    The neuron fires on occurrences of the identifier “File” (especially in Java code), i.e. references to the File class or File-related variables.

    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
     their
    -1.43
    @
    -1.10
    gestone
    -1.07
                
    -1.05
    se
    -1.03
    PreExecute
    -1.02
     các
    -0.98
     they
    -0.97
     juara
    -0.96
    cdn
    -0.96
    POSITIVE LOGITS
    Только
    1.13
    Моя
    1.05
    menuStrip
    1.04
    Цитата
    1.04
     comédie
    1.00
    Jaguar
    0.98
    Mvh
    0.97
    Ещё
    0.97
    Lact
    0.97
    Ваш
    0.96
    Activations Density 0.007%

    No Known Activations