© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5911
    Prev
    Next
    INDEX
    Explanations

    non-english, science, or abbreviations

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

    The neuron responds to rare or unusual tokens—words or strings that occur infrequently (e.g. proper names, trademarks, technical terms, odd punctuation, etc.).

    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
    T
    0.93
    のひとつ
    0.77
    M
    0.77
    F
    0.77
     lange
    0.75
    desde
    0.75
    名は
    0.74
    ἱ
    0.74
     t
    0.73
    TD
    0.73
    POSITIVE LOGITS
    ঙালি
    0.82
    DummyView
    0.79
    ض
    0.79
    ב
    0.79
     Yangzhou
    0.77
     ------------
    0.77
     SupCt
    0.76
     cytochrome
    0.76
     Chhattisgarh
    0.75
    ح
    0.74
    Activations Density 0.000%

    No Known Activations