© 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. 112648
    Prev
    Next
    INDEX
    Explanations

    instantiating java scanner or bufferedreader

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

    the instantiation of Scanner objects in Java code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the Java Scanner class (i.e. the token “Scanner” and its uses).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ↵
    -2.14
    ,’
    -1.75
     $
    -1.65
    ?’
    -1.49
     “
    -1.48
     "
    -1.48
    !’
    -1.43
     $\
    -1.40
    ar
    -1.39
     -
    -1.39
    POSITIVE LOGITS
     of
    2.25
    蹀
    1.76
     indiví
    1.52
     Nuestros
    1.48
    牁
    1.47
     Quien
    1.45
     vosotros
    1.43
     Tienen
    1.42
    呖
    1.41
    rivit
    1.39
    Activations Density 0.001%

    No Known Activations