© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3032
    Prev
    Next
    INDEX
    Explanations

    HTML elements or numbers

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

    This neuron detects numeric tokens—especially floating‐point or integer values—in the text.

    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
    0.66
    0.63
    Promise
    0.57
    0.57
            
    0.56
    0.53
    FileList
    0.52
    #
    0.51
    Base
    0.51
    XML
    0.51
    POSITIVE LOGITS
     viola
    0.68
     violations
    0.56
     violation
    0.55
     violated
    0.54
     violating
    0.53
     violates
    0.53
     violators
    0.52
     nationality
    0.52
     dedicada
    0.52
     firefighting
    0.52
    Activations Density 0.000%

    No Known Activations