© 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. 8283
    Prev
    Next
    INDEX
    Explanations

    brand names and country

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

    The neuron fires on unusually long, multi‐character tokens (i.e. lengthy words).

    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
    s
    0.98
    ga
    0.98
    larda
    0.91
    singular
    0.86
    da
    0.85
    gal
    0.85
    lardan
    0.84
    その他の
    0.82
     otras
    0.81
     afirmar
    0.81
    POSITIVE LOGITS
    ，
    0.69
    нцип
    0.68
     closures
    0.67
     पेड़
    0.67
     encircled
    0.66
    োঁয়া
    0.66
    捨
    0.65
     presidency
    0.64
    墩
    0.63
     synchronization
    0.63
    Activations Density 0.000%

    No Known Activations