© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70956
    Prev
    Next
    INDEX
    Explanations

    noncommutative, HIPAA, activated, flannel

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

    This neuron fires on compound technical adjectives, specifically ones ending in “-around” (as in wraparound) or “-commutative” (as in non-commutative).

    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
     raffredd
    -2.25
     szükséges
    -2.23
     geldi
    -2.16
    ᥬ
    -2.14
     riscal
    -2.11
    ◳
    -2.08
     alugar
    -2.06
    玊
    -2.06
     beiden
    -2.03
    LECTIONS
    -2.03
    POSITIVE LOGITS
    '
    3.09
    :
    2.44
     in
    2.16
    ↵
    2.11
    "
    2.05
     a
    2.03
     or
    2.00
     as
    1.99
     --
    1.98
     for
    1.95
    Activations Density 0.019%

    No Known Activations