© 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. 23905
    Prev
    Next
    INDEX
    Explanations

    physical accumulations or blockages

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

    scientific and medical terms related to deposits, coatings, or formations on surfaces, particularly biological materials like plaques, crusts, and buildups.

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

    The neuron detects terms denoting biological surface deposits or accumulations (e.g. crusts, biofilms, plaques, clots).

    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
     to
    -2.17
     from
    -1.42
     and
    -1.39
    \
    -1.38
     a
    -1.38
    v
    -1.32
     can
    -1.30
    o
    -1.29
     at
    -1.26
    地在
    -1.24
    POSITIVE LOGITS
     literalmente
    1.47
     UNTIL
    1.45
    玊
    1.43
    嶸
    1.34
    薆
    1.34
    entiated
    1.34
    uksen
    1.34
     rempliss
    1.32
     Mereka
    1.30
     eten
    1.29
    Activations Density 0.054%

    No Known Activations