© 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. 83934
    Prev
    Next
    INDEX
    Explanations

    collection size or count

    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
    廰
    -1.77
     just
    -1.58
     described
    -1.49
    遄
    -1.30
     alongside
    -1.30
     conflic
    -1.28
     propri
    -1.26
     and
    -1.26
     barbar
    -1.26
     without
    -1.25
    POSITIVE LOGITS
     innych
    1.65
    还不错
    1.62
     négy
    1.55
     refugiados
    1.53
     seiner
    1.52
    klaim
    1.50
    鱨
    1.49
    tranh
    1.48
    坐在
    1.48
     It
    1.48
    Activations Density 0.002%

    No Known Activations