© 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. 15042
    Prev
    Next
    INDEX
    Explanations

    analyze text

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

    This neuron activates on occurrences of the word “review” (and its morphological variants like “reviewing,” “reviews,” 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
    नन
    0.98
    Liên
    0.98
     หมด
    0.96
    नम
    0.93
    niji
    0.90
     Erweiter
    0.89
     대해서
    0.89
    न
    0.89
     Canadá
    0.88
    ात
    0.87
    POSITIVE LOGITS
    lands
    0.87
     manuscripts
    0.84
     and
    0.84
    and
    0.81
    et
    0.80
     Buccaneers
    0.77
    াত্মক
    0.76
     stocks
    0.75
    leys
    0.75
     suspicious
    0.74
    Activations Density 0.003%

    No Known Activations