© 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. 64527
    Prev
    Next
    INDEX
    Explanations

    explanation of anattā

    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
    --"
    -1.38
     "--
    -1.22
    ..."
    -1.16
     "...
    -1.14
    —"
    -1.11
    &#
    -1.10
    /"
    -1.10
     Arxivat
    -1.08
     ..."
    -1.05
     \"
    -1.05
    POSITIVE LOGITS
    <code>
    1.26
     gerar
    1.16
     leiden
    1.16
    гают
    1.14
    yska
    1.10
     Utilisez
    1.06
     posando
    1.03
    Hình
    1.02
     DialogInterface
    1.02
    <em>
    1.02
    Activations Density 0.008%

    No Known Activations