© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66206
    Prev
    Next
    INDEX
    Explanations

    instrument

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

    The neuron fires on occurrences of the word “instrument” (and its variants like “instruments” or “instrumentation”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    or
    -2.64
     intertwined
    -2.53
    籥
    -2.50
    it
    -2.39
     treacherous
    -2.39
     disgusting
    -2.34
     mundane
    -2.34
     incredibly
    -2.34
    of
    -2.31
     somewhat
    -2.30
    POSITIVE LOGITS
     podrob
    2.39
    蹌
    2.38
     SEÑ
    2.36
    狆
    2.33
     After
    2.30
     maestros
    2.27
    饅
    2.23
    酝
    2.22
     dostup
    2.22
     Many
    2.22
    Activations Density 0.008%

    No Known Activations