© 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. 8140
    Prev
    Next
    INDEX
    Explanations

    currency amounts and names

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

    The neuron selectively activates on numeric tokens and numerical expressions (i.e. digits and numbers).

    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
    rasse
    -0.89
     prices
    -0.85
     monthly
    -0.83
    スパ
    -0.81
    quot
    -0.81
    ѕ
    -0.80
    СУ
    -0.79
    otic
    -0.76
    usted
    -0.75
    leness
    -0.75
    POSITIVE LOGITS
     garota
    0.76
    ورية
    0.76
     promessa
    0.74
    commen
    0.71
    swimming
    0.71
    🦲
    0.71
     annually
    0.71
     Wear
    0.70
    banda
    0.69
     lebih
    0.69
    Activations Density 0.015%

    No Known Activations