© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13399
    Prev
    Next
    INDEX
    Explanations

    related to

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

    The neuron strongly activates on technical or metadata field names and option identifiers (e.g. configuration parameters, tags, or underscored variable names).

    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
    kow
    0.79
    ynski
    0.77
    lama
    0.75
    Ř
    0.75
    ków
    0.74
     FOUND
    0.73
    dü
    0.72
    这份
    0.71
    种种
    0.70
     Гру
    0.69
    POSITIVE LOGITS
    居然
    0.83
    ви
    0.83
    バシー
    0.76
     recente
    0.75
     chiama
    0.75
     ドラ
    0.73
    н
    0.71
    вик
    0.70
     ゼ
    0.70
     nonchal
    0.70
    Activations Density 0.000%

    No Known Activations