© 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. 22-GEMMASCOPE-RES-131K
    7. 16530
    Prev
    Next
    INDEX
    Explanations

    not followed by clarification

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

    The neuron activates on negation cues—especially “not” and “no” (and related phrases) indicating a negative statement.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    愜
    -1.07
     gefeiert
    -1.00
    nable
    -1.00
    ungkap
    -0.98
     花纹
    -0.96
     bénéfices
    -0.96
     zowel
    -0.94
    émie
    -0.92
     eğer
    -0.92
    zzlement
    -0.92
    POSITIVE LOGITS
     but
    1.50
     только
    1.24
     just
    1.23
     because
    1.16
     فقط
    1.15
     tylko
    1.13
     necessarily
    1.00
     only
    0.98
     including
    0.98
    logio
    0.96
    Activations Density 0.031%

    No Known Activations