© 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. 4700
    Prev
    Next
    INDEX
    Explanations

    after quantifiers

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

    This neuron detects numeric category identifiers (floating‐point codes) in backslash‐delimited category paths.

    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
     ईमित्र
    0.86
    зів
    0.84
     स्के
    0.84
    ﺪ
    0.84
    ლი
    0.81
    ⎛
    0.81
     새
    0.80
     بدون
    0.79
    摄像头
    0.78
     टें
    0.78
    POSITIVE LOGITS
    ;
    0.83
    /
    0.64
    ports
    0.64
     actuality
    0.63
    quellen
    0.61
    ,
    0.60
    quelle
    0.57
     if
    0.56
     sources
    0.56
     foci
    0.56
    Activations Density 0.001%

    No Known Activations