© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2905
    Prev
    Next
    INDEX
    Explanations

    distilled water warnings

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

    The neuron is detecting key content words (mostly nouns and descriptive adjectives) as opposed to common function words.

    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
     子供
    0.86
     ragazza
    0.83
    伲
    0.83
     sostenible
    0.81
     controllare
    0.80
    rabbit
    0.80
    sdale
    0.79
     situazione
    0.79
    絴
    0.79
    情况
    0.78
    POSITIVE LOGITS
    UL
    0.76
    ul
    0.75
    ?).
    0.73
    ,
    0.71
    (,
    0.70
    )?,
    0.70
     veya
    0.70
    )—
    0.70
     kas
    0.69
    堂
    0.68
    Activations Density 0.001%

    No Known Activations