© 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. 113375
    Prev
    Next
    INDEX
    Explanations

    class/object declarations like `class Vehicle {`

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

    class names and type declarations in object-oriented programming code.

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

    The neuron fires on user-defined type names (e.g. class or interface identifiers 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
    requipa
    -1.49
    licante
    -1.47
    breviations
    -1.46
    nachron
    -1.42
    madeus
    -1.34
    utentic
    -1.33
     continuación
    -1.33
    ixante
    -1.29
    therosclerosis
    -1.28
    raujo
    -1.25
    POSITIVE LOGITS
     don
    1.23
    ↵
    1.20
    istream
    1.19
    罄
    1.16
     прошло
    1.13
     way
    1.13
     जो
    1.10
     will
    1.09
    ↵↵↵
    1.07
     it
    1.07
    Activations Density 0.080%

    No Known Activations