© 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. 15852
    Prev
    Next
    INDEX
    Explanations

    advertised on platforms

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

    The neuron fires strongly on the first major content word of a new section or paragraph—it’s essentially flagging section/paragraph entry points.

    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
    聽到
    0.80
     Dois
    0.71
     Drives
    0.69
     हुईं
    0.69
     Drž
    0.68
    OV
    0.67
    AZIONE
    0.66
    晛
    0.66
    је
    0.65
    अलग
    0.65
    POSITIVE LOGITS
    ب
    0.95
     formar
    0.85
    schaft
    0.85
    elesaikan
    0.84
    itates
    0.84
     variabel
    0.84
    zir
    0.83
    ون
    0.82
    s
    0.81
     justamente
    0.81
    Activations Density 0.000%

    No Known Activations