© 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. 4641
    Prev
    Next
    INDEX
    Explanations

    words and punctuation

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

    The neuron responds to domain‐specific scientific and medical terminology.

    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
     असून
    1.05
    ませんが
    0.93
    いましたが
    0.92
    ますが
    0.89
    ましたが
    0.86
    きましたが
    0.85
    ]$,
    0.84
    かもしれませんが
    0.84
    었고
    0.84
    '=>'','
    0.83
    POSITIVE LOGITS
    ។
    1.93
    。
    1.91
    .
    1.75
    ۔
    1.73
    ."
    1.67
    .”
    1.66
    ™.
    1.64
    .*
    1.62
    .<
    1.59
    .`
    1.59
    Activations Density 2.148%

    No Known Activations