© 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. 10-GEMMASCOPE-RES-131K
    7. 111559
    Prev
    Next
    INDEX
    Explanations

    Method calls and data access

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

    method calls and property accesses in programming code, particularly those involving capitalized identifiers like "Copy", "Open", "Get", "Path", "Row", and "Save".

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

    This neuron activates on PascalCase identifiers that are API or library method calls in code.

    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
     in
    -2.38
     he
    -1.82
    蚡
    -1.81
    ᯾
    -1.73
     be
    -1.73
    ৄ
    -1.68
     अलावा
    -1.67
     of
    -1.66
    乄
    -1.65
     intrepid
    -1.56
    POSITIVE LOGITS
    Through
    2.13
    Sometimes
    2.09
    "
    1.94
    ⵌ
    1.93
    What
    1.93
    When
    1.87
    Also
    1.86
    Putting
    1.84
    Often
    1.80
    Because
    1.79
    Activations Density 0.034%

    No Known Activations