© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30763
    Prev
    Next
    INDEX
    Explanations

    animated transitions

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

    The neuron activates on numeric tokens—i.e. digit sequences such as code constants, version numbers, or other 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
    atoo
    -0.90
    頁
    -0.74
    Eur
    -0.73
     interconnection
    -0.70
     Mour
    -0.69
    聴
    -0.67
     mackerel
    -0.66
     Definition
    -0.65
     Recht
    -0.65
     Sick
    -0.65
    POSITIVE LOGITS
    πομπ
    0.74
     पार
    0.67
     participe
    0.65
     pts
    0.65
    числен
    0.63
     女人
    0.63
    Sense
    0.63
     CASA
    0.62
     τα
    0.62
     HAND
    0.62
    Activations Density 0.081%

    No Known Activations