© 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. 45438
    Prev
    Next
    INDEX
    Explanations

    most common/prevalent/likely

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

    This neuron detects expressions of frequency or ranking—phrases that indicate how common or prevalent something is (e.g. “most common,” “second most prevalent,” 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
    狆
    -1.76
     großem
    -1.61
     jaké
    -1.58
     sentada
    -1.56
     motocicletas
    -1.49
     desecha
    -1.47
    廝
    -1.46
     céle
    -1.46
    }
    -1.45
     élar
    -1.41
    POSITIVE LOGITS
     of
    2.17
     sesso
    1.54
    ['_
    1.53
    怎
    1.50
     in
    1.42
     contain
    1.42
    ["_
    1.41
    tacular
    1.35
    couvrir
    1.34
     形
    1.34
    Activations Density 0.020%

    No Known Activations