© 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. 10-GEMMASCOPE-RES-131K
    4. 71109
    Prev
    Next
    INDEX
    Explanations

    special characters followed by tokens

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

    The neuron fires on individual numeric digit tokens (especially “1” and “0”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    0
    -1.92
    \
    -1.82
     occasione
    -1.69
    Eight
    -1.68
     meneg
    -1.65
    ↵↵
    -1.63
    ⦊
    -1.61
     ordf
    -1.60
    When
    -1.59
    Seven
    -1.58
    POSITIVE LOGITS
    </b>
    1.75
     we
    1.63
     like
    1.62
     were
    1.50
    汛
    1.49
     They
    1.45
    を含
    1.44
    轳
    1.43
     comuniques
    1.43
    恪
    1.42
    Activations Density 0.007%

    No Known Activations