© 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. 82409
    Prev
    Next
    INDEX
    Explanations

    copyright notices and company names

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

    This neuron detects numeric tokens, especially multi-digit numbers or version-like numeric sequences.

    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
    十八
    -0.69
     mình
    -0.68
    𝙏
    -0.67
    renar
    -0.67
     रख
    -0.66
     poitrine
    -0.66
    Emmanuel
    -0.66
     одна
    -0.66
    íně
    -0.65
    Eleven
    -0.65
    POSITIVE LOGITS
     Laura
    0.74
     Chris
    0.73
    hôpital
    0.70
     fond
    0.68
     twos
    0.68
    我自己
    0.66
    Laura
    0.65
    го
    0.65
     Donna
    0.65
    RODUCTION
    0.65
    Activations Density 0.478%

    No Known Activations