© 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. 8711
    Prev
    Next
    INDEX
    Explanations

    * before * or * almost *

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

    The neuron fires strongly on tokens that mark list-style or section-style enumeration (e.g. “(ii)”, “4” in “(4)”, headings like “Group”, numbered clauses, etc.).

    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
     thorac
    0.80
     ulcers
    0.78
    ಮ
    0.78
     Blynk
    0.77
     jukebox
    0.77
    সম্যান
    0.77
    ]-
    0.76
    ]'
    0.75
     roam
    0.75
     roomy
    0.75
    POSITIVE LOGITS
    occo
    0.78
     inizio
    0.78
    itze
    0.76
    อป
    0.75
    uji
    0.72
    cool
    0.71
    Funny
    0.70
    igis
    0.70
    ాయి
    0.69
    ございます
    0.69
    Activations Density 0.001%

    No Known Activations