© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106171
    Prev
    Next
    INDEX
    Explanations

    big deal or not

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

    This neuron detects hedging or downplaying phrases—especially negations that minimize or soften a statement (e.g. “not a big deal,” “not so bad”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     geograf
    -0.92
    водство
    -0.92
     Hae
    -0.91
    бору
    -0.91
     plati
    -0.90
     indirec
    -0.88
    xically
    -0.86
    WIP
    -0.86
     некоторые
    -0.85
     poros
    -0.85
    POSITIVE LOGITS
     really
    1.42
     major
    1.32
     significant
    1.18
     issue
    1.18
     큰
    1.14
     mattered
    1.07
     problem
    1.04
     terrible
    1.04
     impact
    1.03
     dramatic
    1.03
    Activations Density 0.037%

    No Known Activations