© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14807
    Prev
    Next
    INDEX
    Explanations

    investing in

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

    the neuron detects occurrences of the term “invest” (especially the gerund “investing”).

    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
    摭
    -2.98
    骉
    -2.69
    ሷ
    -2.67
    塤
    -2.66
     puramente
    -2.59
    趼
    -2.56
     altamente
    -2.44
     proveniente
    -2.39
    中期
    -2.38
    
    -2.38
    POSITIVE LOGITS
    s
    2.64
    there
    2.61
     "
    2.52
    after
    2.48
    
    2.44
     wunderbar
    2.36
    妩
    2.31
     способ
    2.31
     nacido
    2.30
    栳
    2.28
    Activations Density 0.003%

    No Known Activations