© 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. 31-GEMMASCOPE-2-RES-16K
    7. 619
    Prev
    Next
    INDEX
    Explanations

    including

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

    The neuron fires on uncommon, multi‐syllable content words—especially technical or domain-specific jargon (e.g. polysyllabic nouns and adjectives).

    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_31_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
    。
    0.59
    、
    0.57
    ？
    0.56
     (?)
    0.54
    の
    0.52
    (?)
    0.52
     の
    0.51
    ，
    0.49
    ،
    0.49
    ։
    0.48
    POSITIVE LOGITS
     including
    1.54
    including
    1.28
     incluindo
    1.27
     включая
    1.22
     incluyendo
    1.21
     včetně
    1.18
     especially
    1.16
     INCLUDING
    1.13
     regardless
    1.12
     termasuk
    1.12
    Activations Density 1.201%

    No Known Activations