© 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. 32738
    Prev
    Next
    INDEX
    Explanations

    current and past assessment

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

    The neuron detects article section headings or titles (e.g. “History and structure,” “Architecture,” “Management and outcome,” etc.).

    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
    existing
    -0.86
     comuniques
    -0.85
    Existing
    -0.84
    یاد
    -0.84
    sores
    -0.84
     已
    -0.83
     Dewey
    -0.83
     YEARS
    -0.82
    gebraucht
    -0.80
     immagine
    -0.79
    POSITIVE LOGITS
     now
    1.02
    ftype
    0.87
     сейчас
    0.86
    icmp
    0.82
     still
    0.81
     current
    0.78
    urrent
    0.73
     評価
    0.73
     séjours
    0.73
    現在
    0.73
    Activations Density 0.180%

    No Known Activations