© 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. 5739
    Prev
    Next
    INDEX
    Explanations

    between ranges

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

    This neuron fires on tokens that introduce new document sections or headings—e.g. block titles, list numbers, or other “lead-in” words at the start of a section.

    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
    킴
    0.88
    ᐟ
    0.86
    强大
    0.85
    强大的
    0.82
    ńczy
    0.79
     więc
    0.77
    间
    0.77
     shy
    0.77
    ্সের
    0.77
    갭
    0.77
    POSITIVE LOGITS
    ಚಾರ
    0.78
    SELF
    0.72
    Eb
    0.71
    TAINS
    0.70
    воре
    0.69
     YE
    0.68
     YOUR
    0.67
    regation
    0.66
    CRIPT
    0.66
    را
    0.66
    Activations Density 0.001%

    No Known Activations