© 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. 22-GEMMASCOPE-RES-131K
    7. 24952
    Prev
    Next
    INDEX
    Explanations

    such followed by noun phrase

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     וכן
    -1.63
    ſſen
    -1.27
     rác
    -1.23
     zanim
    -1.23
     dokumen
    -1.23
     plafon
    -1.20
    legende
    -1.20
    𝐆
    -1.19
     appa
    -1.19
    uesia
    -1.18
    POSITIVE LOGITS
     is
    1.50
    At
    1.47
    It
    1.47
    _
    1.47
    ,
    1.41
    While
    1.40
    -
    1.40
     should
    1.38
     information
    1.35
    ’
    1.35
    Activations Density 0.026%

    No Known Activations