© 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. 34-GEMMASCOPE-RES-131K
    7. 56868
    Prev
    Next
    INDEX
    Explanations

    .NET system namespaces

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    を
    -1.52
    が
    -1.38
    と
    -1.35
    は
    -1.27
    <bos>
    -1.27
    や
    -1.21
    などを
    -1.17
    があり
    -1.13
    それにしても
    -1.12
    虜
    -1.11
    POSITIVE LOGITS
    感じです
    1.28
    ところは
    1.27
    ところに
    1.27
    endimiento
    1.15
    為に
    1.14
    ótico
    1.14
    感じで
    1.14
    の方に
    1.08
     Therefore
    1.08
    there
    1.08
    Activations Density 0.013%

    No Known Activations