© 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. 22-GEMMASCOPE-RES-131K
    7. 80068
    Prev
    Next
    INDEX
    Explanations

    listed alphabetically

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

    The neuron activates on numeric tokens or numerical values (digits, percentages, counts) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    {
    -2.52
    2
    -1.78
    In
    -1.73
    }
    -1.71
     باستخدام
    -1.60
    (
    -1.55
    1
    -1.53
    その
    -1.53
     glimpses
    -1.45
     มัน
    -1.43
    POSITIVE LOGITS
     in
    1.91
     estaban
    1.91
     destacado
    1.83
     fallecido
    1.72
     says
    1.72
    猡
    1.71
     thier
    1.70
     on
    1.69
     navegando
    1.67
    iſter
    1.63
    Activations Density 0.018%

    No Known Activations