© 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. 12265
    Prev
    Next
    INDEX
    Explanations

    labels or keywords

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

    The neuron fires on multi‐word title‐cased phrases that serve as headings or captions (e.g. “Toy and Hobbies Category,” “Fur coat fashion show,” “F-117 takeoff,” etc.).

    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
     H
    0.59
    َن
    0.55
    ops
    0.53
     a
    0.53
    îtes
    0.52
     อ
    0.52
    ographic
    0.52
     Logistics
    0.52
    ‏:‏
    0.52
    activating
    0.52
    POSITIVE LOGITS
    ។
    0.80
     אבל
    0.75
    😥
    0.74
     Nhưng
    0.74
    😸
    0.74
     pero
    0.73
     ¿?
    0.73
     ㅎㅎ
    0.73
    </tr>
    0.70
    👊
    0.70
    Activations Density 0.000%

    No Known Activations