© 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. 75768
    Prev
    Next
    INDEX
    Explanations

    lesson or module sequence

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

    The neuron fires on structural/document-organization tokens—chapter/section headings, unit numbers, and other layout markers.

    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
    γωγ
    -0.86
    cinated
    -0.80
     ajang
    -0.78
    ᕦ
    -0.77
     puntual
    -0.73
     anoche
    -0.73
    estrado
    -0.73
     مبار
    -0.73
     ABSTRACT
    -0.72
    stützung
    -0.72
    POSITIVE LOGITS
     unit
    4.47
     Unit
    4.19
    Unit
    3.95
    unit
    3.50
     units
    3.47
    UNIT
    3.38
     module
    3.36
     Module
    3.14
     Units
    3.11
     UNIT
    3.02
    Activations Density 0.086%

    No Known Activations