© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48256
    Prev
    Next
    INDEX
    Explanations

    actions of entities or groups

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     of
    -2.80
     you
    -2.03
     It
    -1.53
    Filmography
    -1.50
    for
    -1.45
    ків
    -1.44
     by
    -1.41
    你会
    -1.40
    натор
    -1.38
     would
    -1.35
    POSITIVE LOGITS
     involvement
    1.72
     own
    1.60
    んびり
    1.59
     and
    1.55
     extensive
    1.53
    numeros
    1.48
     approval
    1.46
     assists
    1.45
     various
    1.45
     sillas
    1.44
    Activations Density 0.217%

    No Known Activations