© 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. 31566
    Prev
    Next
    INDEX
    Explanations

    Rotary and Kiwanis

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

    This neuron primarily detects numeric tokens (e.g., dates, years, and other multi‐digit 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
    ✥
    -0.78
    quement
    -0.75
     conseillé
    -0.75
    
    -0.75
     خان
    -0.73
    versible
    -0.71
    чным
    -0.71
    kuji
    -0.70
     م
    -0.70
    Davide
    -0.70
    POSITIVE LOGITS
     Rotary
    5.00
    Rotary
    4.03
     rotary
    3.72
     Lions
    3.23
    rotary
    3.13
     Rot
    2.69
    Lions
    2.66
     Ki
    2.38
    Rot
    2.19
     rot
    2.16
    Activations Density 0.027%

    No Known Activations