© 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. 34-GEMMASCOPE-RES-131K
    7. 47262
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    -1.17
     as
    -1.13
     on
    -1.10
     by
    -1.04
     AND
    -1.01
     of
    -0.99
     Honestly
    -0.98
     at
    -0.96
     Did
    -0.96
     with
    -0.94
    POSITIVE LOGITS
     coli
    1.12
     meditación
    1.12
     acoged
    1.09
     aeruginosa
    1.09
    com
    1.07
    org
    1.07
     acestea
    1.04
     таких
    1.02
    Relacion
    1.01
     travailler
    1.00
    Activations Density 0.010%

    No Known Activations