© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101370
    Prev
    Next
    INDEX
    Explanations

    gaining benefits or advantages

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

    The neuron primarily detects numeric values (especially decimal numbers) in the text.

    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
    -1.82
     itself
    -1.45
     into
    -1.27
     you
    -1.22
     lainnya
    -1.21
     at
    -1.20
     stessa
    -1.20
     in
    -1.19
     a
    -1.15
     my
    -1.15
    POSITIVE LOGITS
     җ
    1.53
     kwamba
    1.39
     ۰
    1.34
    詬
    1.31
    uszcz
    1.30
    LAUGHTER
    1.23
    lunda
    1.23
    ковий
    1.23
     سریال
    1.23
    ")->
    1.23
    Activations Density 0.056%

    No Known Activations