© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102010
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases with the

    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
    -2.63
     a
    -1.88
     the
    -1.84
     by
    -1.55
     The
    -1.51
    G
    -1.50
     pentru
    -1.46
     if
    -1.43
     seulement
    -1.43
     we
    -1.40
    POSITIVE LOGITS
     also
    2.17
     and
    1.94
    }{#
    1.71
    
    1.71
     усі
    1.70
    CHREIBUNG
    1.70
     meeste
    1.67
     will
    1.66
    彿
    1.66
    .
    1.65
    Activations Density 0.082%

    No Known Activations