© 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. 15219
    Prev
    Next
    INDEX
    Explanations

    Spark DataFrame

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

    The neuron strongly activates on uncommon or low‐frequency tokens (i.e. words that are rare 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
    ?
    0.88
     tão
    0.80
     мысли
    0.77
     esté
    0.75
     nuestro
    0.73
    은
    0.72
     ayer
    0.71
     reciente
    0.71
     Mariana
    0.71
     связаны
    0.71
    POSITIVE LOGITS
     marginLeft
    0.82
    UIAlert
    0.77
     打
    0.73
     warning
    0.71
     Datenschutz
    0.70
     trespassing
    0.70
    ম্‌
    0.70
    婀
    0.70
    商标
    0.69
    ದಾ
    0.68
    Activations Density 0.000%

    No Known Activations