© 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. 45519
    Prev
    Next
    INDEX
    Explanations

    indicator

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

    The neuron fires on numerical tokens, equation symbols, and other math‐notation elements in technical or LaTeX‐style content.

    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
    RATIO
    -0.74
     RATIO
    -0.73
     diametro
    -0.73
     soya
    -0.72
     ratio
    -0.72
    ratio
    -0.70
    Dossier
    -0.69
    atív
    -0.67
     diablo
    -0.67
    blasts
    -0.67
    POSITIVE LOGITS
     indicator
    3.47
     Indicator
    2.88
     indicators
    2.80
    Indicator
    2.73
    indicator
    2.69
    indicators
    2.27
     INDIC
    2.23
     индика
    2.20
     Indicators
    2.16
    INDICATOR
    2.08
    Activations Density 0.030%

    No Known Activations