© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3029
    Prev
    Next
    INDEX
    Explanations

    file or calculator

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

    The neuron activates most strongly on tokens representing technical identifiers—e.g. file names/extensions (like “.scss”), version or build numbers, and email addresses.

    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_24_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
    活用
    0.51
     electrification
    0.50
     Stations
    0.43
     countenance
    0.43
     swath
    0.42
    িবার
    0.42
     Valuation
    0.42
    薫
    0.42
     disarmament
    0.41
     convoy
    0.41
    POSITIVE LOGITS
     ή
    0.59
     файл
    0.57
     :/
    0.57
     มัน
    0.55
     または
    0.55
     afbeelding
    0.54
     именем
    0.54
     :)
    0.53
     hoặc
    0.53
    :/
    0.51
    Activations Density 0.178%

    No Known Activations