© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39167
    Prev
    Next
    INDEX
    Explanations

    percentages and counts

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

    The neuron activates on numeric tokens (digits and numbers, including decimals).

    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
     so
    -0.81
     когда
    -0.81
    лоси
    -0.78
     BaseController
    -0.78
     For
    -0.76
     (
    -0.75
     Kenney
    -0.74
    又是
    -0.73
     which
    -0.71
     even
    -0.70
    POSITIVE LOGITS
     remainder
    0.98
     actuellement
    0.88
     rest
    0.86
    右边
    0.84
     Suriname
    0.84
    νον
    0.84
     comprimento
    0.84
     perfecte
    0.83
    ǯ
    0.82
     Paragu
    0.82
    Activations Density 0.025%

    No Known Activations