© 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. 22542
    Prev
    Next
    INDEX
    Explanations

    std::

    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
    0
    -1.47
     mnoho
    -1.44
     sabias
    -1.38
    ̍t
    -1.37
    IY
    -1.36
     основных
    -1.36
     peores
    -1.35
    場の
    -1.32
     almendras
    -1.31
     behov
    -1.30
    POSITIVE LOGITS
     this
    2.11
     these
    1.90
     one
    1.86
     These
    1.64
     each
    1.62
     there
    1.48
     selanjutnya
    1.45
     their
    1.44
    包括
    1.38
    cepat
    1.36
    Activations Density 0.150%

    No Known Activations