© 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. 14335
    Prev
    Next
    INDEX
    Explanations

    minimum necessary qualifications

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

    The neuron responds strongly to relatively rare, content-rich words (proper names or less frequent vocabulary) rather than common function 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
    ี
    0.97
    em
    0.95
    ant
    0.88
    ir
    0.88
    w
    0.86
    ied
    0.85
    ec
    0.84
    ring
    0.82
    nd
    0.82
    ud
    0.80
    POSITIVE LOGITS
    Cela
    0.84
    大丈夫
    0.82
     Ці
    0.80
    COMANDA
    0.80
    Vendo
    0.79
    𝒞
    0.79
    🥎
    0.78
    "</
    0.78
    🐐
    0.78
    💴
    0.78
    Activations Density 0.000%

    No Known Activations