© 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. 128020
    Prev
    Next
    INDEX
    Explanations

    equation and mathematical notation blocks

    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
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -1.61
     also
    -1.49
     various
    -1.35
    そして
    -1.29
     some
    -1.24
     this
    -1.21
     other
    -1.15
     specific
    -1.13
    などを
    -1.13
     then
    -1.12
    POSITIVE LOGITS
     necesit
    1.16
    albeit
    1.12
     laisser
    1.09
     éviter
    1.07
    毫无
    1.05
    “
    1.05
    odora
    1.05
    )))),
    1.05
    originally
    1.04
    Hmmm
    1.03
    Activations Density 0.000%

    No Known Activations