© 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. 94123
    Prev
    Next
    INDEX
    Explanations

    copyright and rights notices

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

    The neuron activates on numeric tokens—cardinal numbers, ordinals, years, section or license version numbers, etc.

    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
     FOX
    -0.85
    ancial
    -0.76
    永远
    -0.72
    itulo
    -0.72
     Logger
    -0.70
    アクション
    -0.70
    thouses
    -0.69
    tserrat
    -0.69
    nstein
    -0.69
     Fox
    -0.69
    POSITIVE LOGITS
     discard
    0.79
     flavor
    0.78
    discard
    0.77
     phối
    0.74
     burn
    0.73
     monocytes
    0.72
     veno
    0.71
     Oxid
    0.71
     contrôle
    0.71
     Testing
    0.71
    Activations Density 0.007%

    No Known Activations