© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11181
    Prev
    Next
    INDEX
    Explanations

    2-3 hours, phase 2

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

    The neuron detects numeric sequences, especially multi‐digit identifiers like ISBNs or other long numbers in bibliographic entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Branch
    0.63
    संख्या
    0.62
    Branch
    0.60
     பதி
    0.60
     BRANCH
    0.59
     टाइम्स
    0.58
    BRANCH
    0.56
    
    0.56
     erschienen
    0.55
     نے
    0.55
    POSITIVE LOGITS
     wine
    0.51
    মানব
    0.50
     Throne
    0.50
     করলে
    0.50
     Kahn
    0.49
    [
    0.49
    KeyCode
    0.48
     hyper
    0.48
    FT
    0.48
     appreciation
    0.48
    Activations Density 0.024%

    No Known Activations