© 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. 10-GEMMASCOPE-RES-131K
    7. 20685
    Prev
    Next
    INDEX
    Explanations

    business services

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

    The neuron is tuned to detect mentions of “services” (as in “X services”) in business or company descriptions.

    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
     modificaciones
    -1.51
    も行
    -1.46
    strategia
    -1.45
     réussite
    -1.45
     garantías
    -1.42
     distanza
    -1.39
    我好
    -1.38
     our
    -1.38
     installiert
    -1.38
    exemplar
    -1.37
    POSITIVE LOGITS
    
    1.80
     valide
    1.66
    ("
    1.66
    they
    1.55
    💲
    1.54
     '-':
    1.48
    ¨
    1.48
    ᴀ
    1.45
    me
    1.45
     }));
    1.43
    Activations Density 0.028%

    No Known Activations