© 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. 10-GEMMASCOPE-RES-131K
    7. 22503
    Prev
    Next
    INDEX
    Explanations

    television shows

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

    The neuron fires on terms and punctuation commonly used to introduce or describe television series—titles, seasons, episodes, “series,” “show,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     by
    -1.52
     think
    -1.50
     his
    -1.45
     although
    -1.44
     such
    -1.43
     \
    -1.40
    s
    -1.38
    2
    -1.37
     our
    -1.35
     even
    -1.34
    POSITIVE LOGITS
     fortfarande
    1.47
     vatten
    1.45
     erbjud
    1.42
     ブラウス
    1.42
    ”（
    1.41
    cress
    1.41
    nout
    1.40
     للاسماء
    1.38
    SALUD
    1.38
    щении
    1.38
    Activations Density 0.091%

    No Known Activations