© 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. 91723
    Prev
    Next
    INDEX
    Explanations

    no followed by words of ease

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

    The neuron strongly activates on the token “no,” especially when it appears in emphatic or idiomatic expressions (e.g. “no-brainer,” “no comparison,” “no surprise,” “no real competition”).

    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
     SMALL
    -0.85
     DAM
    -0.85
    Praise
    -0.84
     estimat
    -0.84
    уна
    -0.81
     centru
    -0.80
     INSIDE
    -0.77
     DEEP
    -0.76
     SEVER
    -0.76
     FEW
    -0.76
    POSITIVE LOGITS
    brainer
    2.20
     bra
    2.11
     brain
    1.92
     question
    1.63
    brain
    1.58
     Brain
    1.57
    Brain
    1.49
     contest
    1.48
     questions
    1.45
     Bra
    1.41
    Activations Density 0.025%

    No Known Activations