© 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. 113258
    Prev
    Next
    INDEX
    Explanations

    game or programming context

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

    CamelCase identifiers in programming code, particularly class names, method names, and variable names.

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

    The neuron fires on code‐style identifiers in CamelCase (uppercase-led tokens like WantsToDropItem, InBackpack, Position, etc.).

    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
    ּוֹ
    -1.99
     pouvons
    -1.70
     to
    -1.67
    vegetable
    -1.63
    rifle
    -1.61
    欤
    -1.61
     savons
    -1.59
     sembl
    -1.58
     кроссовки
    -1.58
    ῤ
    -1.57
    POSITIVE LOGITS
    使用
    1.65
    mathrm
    1.62
    _
    1.61
     portatil
    1.60
     нарушения
    1.60
     häufig
    1.59
     trotz
    1.57
    1.56
    ९
    1.54
    _{
    1.53
    Activations Density 0.015%

    No Known Activations