© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13362
    Prev
    Next
    INDEX
    Explanations

    organizing principle, workspace mapping, language, state, virgin birth, adjusting

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

    The neuron fires on words that begin new paragraphs or sections (i.e. the first token after a break).

    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
    URANCE
    0.74
     compren
    0.73
    आर
    0.71
     bianca
    0.71
    산
    0.68
    ДИ
    0.67
    나
    0.66
    Allow
    0.66
     гре
    0.66
    UIC
    0.66
    POSITIVE LOGITS
     Ordinance
    0.90
     appreciable
    0.84
     Endocrinology
    0.84
     summed
    0.81
    曌
    0.81
     Karate
    0.78
     cortos
    0.78
     Gases
    0.78
     ferret
    0.78
     কহ
    0.77
    Activations Density 0.000%

    No Known Activations