© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9316
    Prev
    Next
    INDEX
    Explanations

    admissionOpusAndroidLonggroupapproxSwap

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

    The neuron fires on unusually rare or low‐frequency tokens—e.g. brand/model names, alphanumeric codes, and other out‐of‐vocabulary or highly specific terms.

    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
    ្សែ
    0.88
     പറയുന്നത്
    0.85
    ты
    0.83
     constaté
    0.83
    ದ
    0.83
    ки
    0.82
     obligé
    0.81
    䄪
    0.81
     اظہار
    0.79
     potenciales
    0.79
    POSITIVE LOGITS
    kách
    0.72
    ftone
    0.71
    nim
    0.70
    inson
    0.66
    .•
    0.65
    an
    0.64
    πη
    0.64
    es
    0.63
    fta
    0.63
    sız
    0.62
    Activations Density 0.001%

    No Known Activations