© 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. 6162
    Prev
    Next
    INDEX
    Explanations

    programming syntax, variables, or special characters

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

    The neuron detects monetary amounts (currency symbols followed by numeric values).

    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
    πό
    0.70
    ⓶
    0.66
    quarter
    0.64
    मेस्टर
    0.64
    ཙ
    0.64
    bok
    0.64
    ἢ
    0.63
     عايز
    0.61
    镌
    0.61
     capac
    0.60
    POSITIVE LOGITS
    ('[
    0.71
    ^+$
    0.63
    ($
    0.60
     俺
    0.60
    ellas
    0.59
    ^{(
    0.58
    rootScope
    0.54
     (!$
    0.54
    ','$
    0.54
    ("$
    0.53
    Activations Density 0.049%

    No Known Activations