© 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. 7759
    Prev
    Next
    INDEX
    Explanations

    variable assignments and definitions

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

    The neuron strongly activates on uppercase alphanumeric identifiers (often containing underscores, hyphens, or digit sequences), such as database accession codes, DOIs, or other technical field names.

    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
     oznac
    0.68
     त्यांनी
    0.58
     Youth
    0.57
     طالب
    0.55
     gosto
    0.55
     SalesLT
    0.55
     Bunda
    0.54
     /(
    0.54
     något
    0.54
     Arti
    0.53
    POSITIVE LOGITS
    $_
    0.74
    _
    0.72
    $
    0.71
    1
    0.70
    $-$
    0.69
    '_
    0.68
    -_
    0.68
    $-
    0.67
    2
    0.66
    0
    0.65
    Activations Density 0.010%

    No Known Activations