© 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. 103270
    Prev
    Next
    INDEX
    Explanations

    legal citations, especially appellant

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

    The neuron strongly activates on CamelCase technical identifiers in code (e.g. MemoryStream, ApiModelProperty, Initialized), singling out Pascal‐case API or library class/member names.

    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
     「
    -2.13
     deft
    -2.11
     YOUR
    -2.05
     grâce
    -2.02
     BOTH
    -1.97
     MUCH
    -1.95
     THEIR
    -1.90
     !!!!
    -1.88
     THAT
    -1.88
     ????
    -1.88
    POSITIVE LOGITS
    狁
    1.84
    )”
    1.84
     him
    1.75
    なんですね
    1.75
    ']
    1.73
    思议
    1.71
     lutar
    1.66
    攆
    1.66
     magnitud
    1.65
     男士
    1.63
    Activations Density 0.001%

    No Known Activations