© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45421
    Prev
    Next
    INDEX
    Explanations

    http url patterns

    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
    "
    -1.55
    вались
    -1.55
    別の
    -1.54
    ного
    -1.53
    K
    -1.46
    了一会儿
    -1.45
    H
    -1.45
    𖣘
    -1.44
    Prefix
    -1.42
    N
    -1.42
    POSITIVE LOGITS
     the
    1.73
     that
    1.64
     and
    1.59
     of
    1.44
     with
    1.40
     kembali
    1.38
     journalistes
    1.36
     bersama
    1.35
     some
    1.34
     project
    1.34
    Activations Density 0.002%

    No Known Activations