© 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. 7165
    Prev
    Next
    INDEX
    Explanations

    hypothetical statements and possibilities

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

    The neuron preferentially activates on mid‐frequency “content” words (neither extremely common stopwords nor rare specialized terms).

    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
    /*
    0.77
    taxes
    0.71
    ="
    0.70
     bằng
    0.70
    untary
    0.70
     emberek
    0.69
    ח
    0.69
    빡
    0.69
     aziende
    0.69
    **)
    0.68
    POSITIVE LOGITS
    ously
    0.73
    buty
    0.73
    TGFuZ
    0.73
     रिपोर्ट्स
    0.73
    ीडियो
    0.71
    зировать
    0.70
    сная
    0.70
     heartache
    0.70
    יות
    0.70
     seemingly
    0.68
    Activations Density 0.000%

    No Known Activations