© 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. 9689
    Prev
    Next
    INDEX
    Explanations

    instructor/#skill or instructor/qualities

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

    The neuron fires most strongly on low‐frequency, uncommon tokens—i.e. it flags rare or outlier words in the text.

    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
     parte
    0.74
    ปก
    0.71
     heller
    0.70
    rg
    0.68
    सेंट
    0.68
     अग्र
    0.68
    อ
    0.68
     Spicer
    0.68
    ut
    0.67
    H
    0.64
    POSITIVE LOGITS
    ında
    0.90
    années
    0.83
     renverse
    0.82
     conduire
    0.81
     renvers
    0.81
    ستوى
    0.80
    ₁,
    0.79
     heureux
    0.79
    偿
    0.79
    CHCl
    0.78
    Activations Density 0.000%

    No Known Activations