© 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. 15565
    Prev
    Next
    INDEX
    Explanations

    natural terrains and regions

    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
     a
    -1.56
    REQUIRED
    -1.55
    ísimas
    -1.51
    wiście
    -1.48
    podob
    -1.36
    ");
    -1.30
    ILL
    -1.29
    pAd
    -1.29
    Actually
    -1.28
    members
    -1.27
    POSITIVE LOGITS
    ."
    1.77
    s
    1.66
     are
    1.59
     reconoci
    1.45
    jenigen
    1.42
    .'”
    1.40
     feststellen
    1.37
     '
    1.34
    perature
    1.33
     речо
    1.30
    Activations Density 0.062%

    No Known Activations