© 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. 90682
    Prev
    Next
    INDEX
    Explanations

    HTML links and code snippets

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

    The neuron activates on numeric literals (digits or numbers) in code/markup (e.g. attribute values, dimensions, URLs).

    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
    ⁻
    -0.84
    መ
    -0.82
     Person
    -0.79
     quartier
    -0.79
    abd
    -0.77
    Toul
    -0.77
    inp
    -0.77
     agence
    -0.76
    鄂
    -0.76
     Rück
    -0.75
    POSITIVE LOGITS
     rel
    1.23
    rel
    1.02
    noopener
    0.93
     related
    0.89
    أو
    0.87
     noop
    0.86
     Erkrank
    0.85
    itinéraire
    0.83
    Without
    0.82
    EXTERNAL
    0.81
    Activations Density 0.004%

    No Known Activations