© 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. 16602
    Prev
    Next
    INDEX
    Explanations

    historical context

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

    The main thing this neuron does is detect salient domain-specific keywords (technical or topic-signaling nouns and verbs) that mark shifts in subject matter.

    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
    じた
    -0.91
    ɗ
    -0.85
    Maße
    -0.82
     aumentare
    -0.81
    WebpackPlugin
    -0.81
     kín
    -0.81
    érico
    -0.80
    鄞
    -0.80
     Multil
    -0.79
    ◞
    -0.79
    POSITIVE LOGITS
    </h5>
    0.83
     petro
    0.82
     permasalahan
    0.82
    Crus
    0.80
    ldr
    0.77
     cellular
    0.76
    </h4>
    0.76
     berdiri
    0.75
    人には
    0.74
    咖啡
    0.72
    Activations Density 0.277%

    No Known Activations