© 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. 25026
    Prev
    Next
    INDEX
    Explanations

    NOTE followed by colon

    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
    Negative Logits
    máy
    -1.12
    filosof
    -1.09
    )}+
    -1.08
    denied
    -1.05
    <bos>
    -1.04
    paket
    -1.03
     rám
    -1.02
    ompi
    -1.02
    彇
    -1.02
    İş
    -1.01
    POSITIVE LOGITS
     this
    1.94
     that
    1.83
     there
    1.53
     may
    1.39
    n
    1.37
     only
    1.30
     these
    1.23
    This
    1.19
     might
    1.18
     actually
    1.17
    Activations Density 0.019%

    No Known Activations