© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82970
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives

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

    The neuron fires on very high‐frequency tokens—common words or symbols that occur often across documents.

    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
    黑的
    -1.22
     "
    -1.03
     '
    -0.95
     Schulen
    -0.94
     अपने
    -0.89
    aliment
    -0.89
     治療
    -0.88
     etwa
    -0.88
     décadas
    -0.87
     cuándo
    -0.86
    POSITIVE LOGITS
    很赞
    1.00
    デル
    0.94
     svi
    0.92
     peluche
    0.91
     garantir
    0.91
     voo
    0.89
     effici
    0.89
     Golfo
    0.89
    ––
    0.88
     =-\
    0.88
    Activations Density 0.000%

    No Known Activations