© 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. 38141
    Prev
    Next
    INDEX
    Explanations

    data assignment

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

    The neuron strongly activates on programming identifier tokens (e.g. variable or constant names 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
    áles
    -1.12
     обычно
    -0.96
    gettyimages
    -0.95
     Гі
    -0.94
     humedad
    -0.92
     spelen
    -0.90
     exatamente
    -0.90
     bilgiler
    -0.90
     dragen
    -0.89
     betalen
    -0.88
    POSITIVE LOGITS
     ambayo
    1.17
    ?」
    1.10
     skola
    1.05
    ……”
    1.02
    .}(
    1.00
     ,.
    0.99
    ENSIS
    0.98
    ?”
    0.98
    ANDUM
    0.96
    ——”
    0.96
    Activations Density 0.071%

    No Known Activations