© 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. 68618
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Top"

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

    The neuron detects occurrences of the word “Top” as used in list-style headings (e.g. “Top 10,” “Top 132,” 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     
    -4.69
    (
    -4.06
    -
    -3.41
    *
    -3.28
    $
    -3.27
    '
    -3.20
    \
    -3.16
    +
    -3.08
    "
    -3.05
    1
    -2.97
    POSITIVE LOGITS
    ѣмъ
    3.47
    commodation
    3.33
    ſſi
    3.23
    ሖ
    3.16
    胧
    2.97
    ésil
    2.94
     园
    2.89
    ୈ
    2.89
    archiwizowane
    2.89
    êmio
    2.89
    Activations Density 0.004%

    No Known Activations