© 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. 98834
    Prev
    Next
    INDEX
    Explanations

    constraints, annotations, Mvc, Required

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

    The neuron fires on programming identifiers and keywords—things like class or namespace names, library/types identifiers, and annotation or markup tags 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_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
    ipheral
    -0.86
     much
    -0.83
     동안
    -0.82
    ꪮ
    -0.82
     downside
    -0.79
    ()")
    -0.78
     しま
    -0.78
     unlike
    -0.77
     Panic
    -0.75
    خوان
    -0.75
    POSITIVE LOGITS
     pól
    0.89
     regex
    0.86
    Annotations
    0.85
     SWITCH
    0.81
     annotation
    0.80
     koncep
    0.79
    szám
    0.77
     PRA
    0.76
    attribute
    0.76
    Requ
    0.76
    Activations Density 0.001%

    No Known Activations