© 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. 8
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to the start‐of‐text or sentence boundary marker (i.e. it fires on the very beginning of each segment).

    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
     +
    0.26
    +
    0.26
    에
    0.26
     with
    0.25
    1
    0.25
    ＆
    0.25
     &
    0.24
     only
    0.24
     которой
    0.24
    を
    0.24
    POSITIVE LOGITS
     வகையான
    0.31
     entidades
    0.30
     entities
    0.29
     maladies
    0.29
     governmental
    0.28
     ailments
    0.28
     spesies
    0.26
     ogran
    0.26
     illnesses
    0.25
     fornis
    0.25
    Activations Density 16.926%

    No Known Activations