© 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. 34-GEMMASCOPE-RES-131K
    7. 1461
    Prev
    Next
    INDEX
    Explanations

    dedication and contribution

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

    This neuron detects enthusiastic corporate marketing or promotional jargon—buzzword-heavy phrases used in business or sales copy.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    kaç
    -0.84
     expresiones
    -0.83
     巧克力
    -0.81
     betrek
    -0.81
    urée
    -0.81
     sensaciones
    -0.79
    บาง
    -0.79
    características
    -0.78
    炜
    -0.77
    
    -0.77
    POSITIVE LOGITS
     vow
    0.96
     dedic
    0.91
     contribute
    0.90
     strug
    0.88
     strive
    0.87
     responsibility
    0.87
     dedication
    0.86
     contribution
    0.85
     persistence
    0.84
     determinations
    0.84
    Activations Density 0.008%

    No Known Activations