© 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. 83707
    Prev
    Next
    INDEX
    Explanations

    adjoining or adjacent

    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
    Negative Logits
    .
    -2.41
    <td>
    -1.79
    ernacle
    -1.59
    "../
    -1.51
     ダウン
    -1.45
    Ли
    -1.41
    ार
    -1.41
    و
    -1.39
     Vols
    -1.38
    "{\
    -1.38
    POSITIVE LOGITS
     but
    1.84
     these
    1.79
     the
    1.66
     colder
    1.63
     этих
    1.55
     bahkan
    1.52
     pretende
    1.52
    関連リンク
    1.50
    ୌ
    1.48
    Klem
    1.47
    Activations Density 0.050%

    No Known Activations