© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4540
    Prev
    Next
    INDEX
    Explanations

    9

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

    The neuron detects asterisks (e.g. “*”) used as markers for bullet points or list items.

    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
     largura
    0.80
     tamanho
    0.78
     Erweiter
    0.78
    И
    0.73
     tellement
    0.70
    кова
    0.68
    कई
    0.68
     Größe
    0.66
    vertexBuffer
    0.66
     mehrerer
    0.66
    POSITIVE LOGITS
    adika
    0.70
     TRY
    0.68
    ウト
    0.66
    ᆻ
    0.65
    丅
    0.65
    hammad
    0.64
     SERVICES
    0.64
    ilah
    0.63
     الصنا
    0.63
     타
    0.62
    Activations Density 0.038%

    No Known Activations