© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34338
    Prev
    Next
    INDEX
    Explanations

    class inheritance and generics

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

    This neuron is specialized for spotting generic‐type parameter constraint syntax (e.g. the “T : SomeType” or “extends” parts) 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_22/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
     commandement
    -1.35
    蛱
    -1.34
     ilha
    -1.28
    ’
    -1.23
    蛧
    -1.23
    umers
    -1.23
     própri
    -1.23
     Cette
    -1.16
    etal
    -1.13
    sejarah
    -1.13
    POSITIVE LOGITS
     like
    1.42
     of
    1.40
     described
    1.25
     estándares
    1.24
     in
    1.22
     -
    1.21
     organismos
    1.20
     comercio
    1.19
     zwykle
    1.18
     rápidos
    1.16
    Activations Density 0.002%

    No Known Activations