© 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. 42177
    Prev
    Next
    INDEX
    Explanations

    suitability and physical fit

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

    The neuron fires almost exclusively on the word “fitting” (and its plural “fittings”), i.e. it detects that exact token wherever it appears.

    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
    j
    -2.92
    s
    -2.77
    z
    -2.67
    \
    -2.64
    ᕦ
    -2.28
    놋
    -2.23
    是
    -2.20
    *
    -2.16
     хора
    -2.16
    k
    -2.11
    POSITIVE LOGITS
    觏
    2.59
     Remaining
    2.47
     Slightly
    2.42
    与此同时
    2.42
     Rather
    2.42
    ൎ
    2.28
     relativamente
    2.27
    ࿊
    2.25
    からお
    2.25
     Somewhat
    2.23
    Activations Density 0.002%

    No Known Activations