© 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. 9372
    Prev
    Next
    INDEX
    Explanations

    conj: unctive"

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

    The neuron is sensitive to uncommon, high–information (i.e. low-frequency) content 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
     attenzione
    0.98
    ség
    0.86
    𝙫
    0.86
     agh
    0.83
     vre
    0.81
    ים
    0.80
    טים
    0.80
    sour
    0.79
     triste
    0.79
     exquis
    0.79
    POSITIVE LOGITS
    й
    1.09
    е
    0.82
     Это
    0.80
     Этот
    0.79
     চক্র
    0.78
     Tento
    0.77
    ยนต์
    0.76
     Thats
    0.75
    UM
    0.74
     Red
    0.74
    Activations Density 0.000%

    No Known Activations