© 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. 3730
    Prev
    Next
    INDEX
    Explanations

    useCallback, Go

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

    The neuron strongly activates on tokens that start new sentences (i.e. sentence-initial 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
    ธุรก
    0.68
     renowned
    0.64
    大规模
    0.63
    戦略
    0.59
    หาก
    0.57
    Hvis
    0.57
    轰
    0.56
     weltweit
    0.55
     prestig
    0.54
    競爭
    0.54
    POSITIVE LOGITS
     carbox
    0.70
     जो
    0.64
     灬
    0.63
     mehndi
    0.63
     ∠
    0.63
     우리
    0.62
     gentamicin
    0.62
    ,_-
    0.61
     항상
    0.61
     alright
    0.61
    Activations Density 0.116%

    No Known Activations