© 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. 10304
    Prev
    Next
    INDEX
    Explanations

    Zero-Point Field

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

    The main thing this neuron does is flag extremely rare or out‐of‐distribution tokens (i.e. unusually infrequent words or symbols).

    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
     אבל
    0.78
     Yvonne
    0.77
     Amiri
    0.76
     Kotor
    0.75
     autoradi
    0.75
    uram
    0.72
    ษ
    0.72
    ۰۰
    0.72
    ваи
    0.72
     successive
    0.71
    POSITIVE LOGITS
    SBS
    0.82
    伽
    0.82
     보자
    0.78
    ти
    0.77
    contrast
    0.77
    emples
    0.73
     séparation
    0.73
    ദ
    0.72
    Contributor
    0.71
    ități
    0.71
    Activations Density 0.000%

    No Known Activations