© 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. 75871
    Prev
    Next
    INDEX
    Explanations

    lakh

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

    The neuron strongly activates on numeric tokens—especially digits and currency/price figures—i.e. values denoting amounts or measurements.

    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
     crore
    -0.96
     crores
    -0.93
     billions
    -0.84
    LogLevel
    -0.76
    adhé
    -0.73
     Doria
    -0.73
     sessionId
    -0.71
     ریزی
    -0.71
    тропо
    -0.71
     Jenna
    -0.69
    POSITIVE LOGITS
     lac
    1.05
     लाख
    0.87
     lakh
    0.84
     خمس
    0.81
    Attempt
    0.77
    wann
    0.77
    Forever
    0.76
    装甲
    0.71
    Five
    0.71
    lac
    0.70
    Activations Density 0.024%

    No Known Activations