© 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. 65705
    Prev
    Next
    INDEX
    Explanations

    studies and effects following hyphens

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

    The neuron strongly activates on numeric tokens (digits, years, counts, and other number strings).

    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
     Կ
    -0.73
     התח
    -0.72
    タオル
    -0.70
     Liter
    -0.69
     spille
    -0.67
     февраля
    -0.67
     olvides
    -0.67
    擇
    -0.66
     Hid
    -0.65
     numerator
    -0.65
    POSITIVE LOGITS
    ERIC
    1.45
     ERIC
    1.27
    BEST
    1.04
    最佳
    0.93
    дят
    0.85
    eric
    0.84
    controlled
    0.83
    EDO
    0.81
    ęgn
    0.81
    Might
    0.81
    Activations Density 0.007%

    No Known Activations