© 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. 72005
    Prev
    Next
    INDEX
    Explanations

    variable names and code constructs

    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
     and
    -2.06
     is
    -1.30
    ↵↵↵↵↵↵↵↵↵↵
    -1.26
     was
    -1.22
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.17
     handicap
    -1.15
    ↵↵↵↵↵↵↵↵↵
    -1.14
    の新
    -1.12
    mazioni
    -1.09
    ↵↵↵↵↵↵↵↵
    -1.07
    POSITIVE LOGITS
     mengucap
    1.66
     its
    1.62
    çou
    1.54
     corris
    1.42
     menegaskan
    1.38
    也不會
    1.38
     mengucapkan
    1.38
     there
    1.38
     ciepła
    1.34
     corazones
    1.33
    Activations Density 0.025%

    No Known Activations