© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66266
    Prev
    Next
    INDEX
    Explanations

    no cost or hassle

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

    This neuron detects the word “no” when used in promotional or offer contexts (e.g. “no minimum order,” “no waiting,” “no catch,” etc.).

    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
     могла
    -0.84
     provocar
    -0.82
    それから
    -0.82
     afirmar
    -0.81
    ILLON
    -0.80
    urre
    -0.79
     labios
    -0.78
     jelasnya
    -0.78
     Tren
    -0.76
    меры
    -0.76
    POSITIVE LOGITS
     hidden
    1.42
     need
    1.20
     waiting
    1.14
    hidden
    1.14
     hassle
    1.04
     obligation
    1.04
    complicated
    1.03
     complicated
    1.02
    wait
    1.02
     muss
    1.02
    Activations Density 0.039%

    No Known Activations