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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59110
    Prev
    Next
    INDEX
    Explanations

    the specific attribute

    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
    浓郁
    -1.67
     điệu
    -1.67
    trze
    -1.64
     acqua
    -1.63
    Berikut
    -1.62
    也将
    -1.62
    巔
    -1.60
    3
    -1.58
    细腻
    -1.58
     Frankrijk
    -1.58
    POSITIVE LOGITS
     then
    2.55
     to
    2.55
     is
    2.53
     of
    2.50
     they
    2.17
     being
    2.16
     about
    2.16
     for
    2.11
     not
    2.09
     without
    2.06
    Activations Density 0.025%

    No Known Activations