© 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. 104758
    Prev
    Next
    INDEX
    Explanations

    programming constructs and identifiers

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

    The neuron responds to isolated uppercase‐or‐titlecase tokens that serve as section headings, module/library names, or other standalone identifiers.

    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
    參考文獻
    -1.10
     apartament
    -1.09
     departament
    -1.09
     情人
    -1.06
     idyl
    -1.06
     relais
    -1.05
     biografi
    -1.05
    ungkap
    -1.05
     电脑
    -1.02
     客户
    -1.01
    POSITIVE LOGITS
     cómodo
    1.13
     energías
    1.09
    為に
    1.07
     mocno
    0.99
    _
    0.97
     betreft
    0.97
     say
    0.96
     your
    0.95
    bred
    0.95
     //
    0.93
    Activations Density 0.001%

    No Known Activations