© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6203
    Prev
    Next
    INDEX
    Explanations

    f following other tokens

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

    This neuron fires on tokens that are numeric (digits or hex-digit sequences), for example parts of color codes or other numbers.

    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
    ategy
    0.73
    schule
    0.70
    abilità
    0.69
    aujourd
    0.69
    هاي
    0.66
     SimSun
    0.66
    ங்கிணை
    0.65
     સંપૂર્ણ
    0.65
     ampia
    0.65
     ആദ്യം
    0.65
    POSITIVE LOGITS
    black
    0.54
     emiss
    0.54
     sulfur
    0.53
    <0xA2>
    0.51
     vapor
    0.51
     lineColor
    0.50
     white
    0.49
     tint
    0.48
     charges
    0.48
     charcoal
    0.48
    Activations Density 0.000%

    No Known Activations