© 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. 7405
    Prev
    Next
    INDEX
    Explanations

    question and

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

    The neuron fires on prominent action verbs—especially those in –ing or other inflected forms—that mark key dynamic or informational content in a sentence.

    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
     wrangler
    0.74
    優秀
    0.67
    𓇼
    0.67
     stalls
    0.67
    ববার
    0.67
    گے
    0.66
    หนึ่ง
    0.66
    衙
    0.66
     estreia
    0.66
    स्थ्य
    0.65
    POSITIVE LOGITS
     vacuna
    0.87
    }">
    0.80
    м
    0.78
    }"
    0.75
    }->
    0.75
    }",
    0.73
     случае
    0.73
    ς
    0.72
    лив
    0.71
     объяс
    0.70
    Activations Density 0.000%

    No Known Activations