© 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. 22-GEMMASCOPE-RES-131K
    4. 27810
    Prev
    Next
    INDEX
    Explanations

    small businesses and SMEs

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

    The neuron activates on mentions of small- or medium-sized businesses (e.g. “SMEs,” “small business,” “SMB”).

    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
     asume
    -1.26
     búsquedas
    -1.23
    mbal
    -1.21
    感じです
    -1.20
     grego
    -1.20
    久し
    -1.18
    𝗳
    -1.16
    ξύ
    -1.15
     desn
    -1.13
     exceeding
    -1.11
    POSITIVE LOGITS
     kecil
    1.73
     small
    1.54
    small
    1.33
     (<
    1.32
     الصغيرة
    1.29
    เล็ก
    1.13
     in
    1.11
    </em>
    1.11
     často
    1.11
     nhỏ
    1.09
    Activations Density 0.027%

    No Known Activations