© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61413
    Prev
    Next
    INDEX
    Explanations

    smooth muscle

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

    the word "smooth" and related terms describing even or continuous surfaces/movements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on occurrences of the word “smooth” (including variations like “smoothing”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -4.84
     REALLY
    -3.48
     AMAZING
    -3.44
     unbelievably
    -3.28
     insanely
    -3.22
     delightfully
    -3.19
     VERY
    -3.19
     ridiculously
    -3.17
     alcune
    -3.09
     MOST
    -3.02
    POSITIVE LOGITS
    鋮
    3.31
    晅
    3.08
     tramontina
    3.02
    龃
    3.02
    嬗
    3.00
     onPostExecute
    2.98
    '
    2.97
    ～。
    2.91
    يقة
    2.89
     科技
    2.84
    Activations Density 0.007%

    No Known Activations