© 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. 14091
    Prev
    Next
    INDEX
    Explanations

    word: or phrase

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

    The neuron strongly activates on relatively low-frequency, content-bearing tokens (i.e. rare “keyword” words or technical terms) 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
    T
    0.93
    i
    0.91
    ↵
    0.90
    0
    0.84
     t
    0.81
    F
    0.77
    Ві
    0.76
    Y
    0.75
    C
    0.75
    V
    0.75
    POSITIVE LOGITS
     glLightfv
    0.88
     sorprendente
    0.86
     sparsebundle
    0.85
    の違い
    0.84
     baryons
    0.82
     Servlet
    0.81
     rutina
    0.80
     proporcionan
    0.79
     deceiving
    0.79
     aparelho
    0.79
    Activations Density 0.000%

    No Known Activations