© 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. 70
    Prev
    Next
    INDEX
    Explanations

    as requested

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

    The neuron strongly activates on the coordinating phrase “as well.”

    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
    ()
    0.36
    .
    0.33
    ');
    0.32
    '};
    0.31
    }
    0.31
     หรือ
    0.30
    '
    0.30
    ה
    0.29
    ',
    0.28
    \/
    0.28
    POSITIVE LOGITS
     evidenced
    0.37
    sembles
    0.36
    ર
    0.32
    វា
    0.31
    it
    0.30
     তারা
    0.29
    reements
    0.29
    ımın
    0.29
    毕竟
    0.28
    要知道
    0.28
    Activations Density 0.626%

    No Known Activations