© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118067
    Prev
    Next
    INDEX
    Explanations

    code declarations and types

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

    This neuron detects code identifiers that name or reference types (e.g. class, struct, namespace, or other user‐defined type 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_34/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
    but
    -0.81
    躊
    -0.80
     mahu
    -0.80
    having
    -0.79
     posso
    -0.79
     sull
    -0.79
     firme
    -0.79
     öf
    -0.77
     péro
    -0.77
     América
    -0.76
    POSITIVE LOGITS
    WEBPACK
    0.92
     階段
    0.91
     ながら
    0.87
     Tuttavia
    0.85
     jpg
    0.85
    setzen
    0.85
     SiO
    0.84
     Achieve
    0.84
     Insta
    0.83
     込
    0.83
    Activations Density 0.069%

    No Known Activations