© 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. 8335
    Prev
    Next
    INDEX
    Explanations

    lists, comparison, XOR, optionally create

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

    The neuron strongly activates on the very first content token of a new segment or paragraph (i.e. the initial word 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
    ت
    0.88
    s
    0.80
    ल
    0.80
    рист
    0.79
    d
    0.75
    tat
    0.74
    лений
    0.72
    ↵
    0.71
    t
    0.69
    0
    0.69
    POSITIVE LOGITS
    ంక
    0.75
     उठाकर
    0.72
     वॉटर
    0.72
    ្សែ
    0.71
    vadipine
    0.71
     الناتج
    0.70
     صنایع
    0.70
     avendo
    0.70
     marchés
    0.69
     dilwale
    0.68
    Activations Density 0.000%

    No Known Activations