© 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. 22-GEMMASCOPE-RES-131K
    7. 68290
    Prev
    Next
    INDEX
    Explanations

    code components and structures

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

    This neuron detects code tokens that are capitalized type or class identifiers (e.g. framework, class, or interface 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_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
     registró
    -1.02
     markiert
    -0.99
    Comté
    -0.95
    ahme
    -0.94
    saves
    -0.92
    theres
    -0.91
     beş
    -0.90
    ığımız
    -0.90
     espectaculares
    -0.90
    soluble
    -0.89
    POSITIVE LOGITS
     нарушения
    1.03
     Minangkabau
    1.02
     should
    0.95
     DKI
    0.94
     Banjar
    0.93
     Huerta
    0.93
    vinger
    0.93
    ofte
    0.92
     Kela
    0.91
    ু
    0.91
    Activations Density 0.006%

    No Known Activations