© 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. 64528
    Prev
    Next
    INDEX
    Explanations

    sequences or comparisons

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

    This neuron fires on short title-style or call-to-action phrases made up of capitalized words (e.g. “The Full Story,” “Buy From,” “Book a …”).

    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
    ditionally
    -1.01
    López
    -0.98
    ことが
    -0.90
    
    -0.90
     hierdie
    -0.88
    QCD
    -0.88
     zwykle
    -0.88
     its
    -0.88
    miter
    -0.87
    García
    -0.84
    POSITIVE LOGITS
    </h2>
    1.10
    恐怕
    0.96
    isDead
    0.96
     vejo
    0.94
    もあるので
    0.94
     schuhe
    0.94
     alcuni
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.93
    rt
    0.92
    是怎么回事
    0.92
    Activations Density 0.013%

    No Known Activations