© 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. 116569
    Prev
    Next
    INDEX
    Explanations

    required before

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

    The neuron strongly activates on tokens that consist of or contain numeric digits.

    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
     Edelman
    -0.70
     measurement
    -0.69
    Zahl
    -0.66
    の紹介
    -0.65
    امه
    -0.63
    싼
    -0.63
    EClass
    -0.63
    HasColumnType
    -0.63
    Agua
    -0.61
     Fros
    -0.61
    POSITIVE LOGITS
     Startups
    0.71
     Cure
    0.69
    blox
    0.68
    Dominique
    0.68
    бав
    0.67
    ปล
    0.66
    śred
    0.65
    
    0.65
    synap
    0.65
    ufact
    0.64
    Activations Density 0.070%

    No Known Activations