© 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. 22639
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
     also
    -2.73
     This
    -2.06
    隄
    -1.73
     There
    -1.73
    Also
    -1.70
     Only
    -1.66
    嬤
    -1.63
     sierpnia
    -1.61
     lipca
    -1.59
    This
    -1.59
    POSITIVE LOGITS
     we
    1.69
    Ummm
    1.64
     foray
    1.64
     acoged
    1.59
     dieß
    1.58
    komme
    1.58
    立马
    1.56
     kabát
    1.55
     vimos
    1.51
     hornear
    1.48
    Activations Density 0.024%

    No Known Activations