© 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. 127766
    Prev
    Next
    INDEX
    Explanations

    scaling numbers and random values

    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
     pattes
    -1.20
     triomphe
    -1.15
    Adres
    -1.15
     illustre
    -1.11
    Interes
    -1.09
     jambes
    -1.09
    Meto
    -1.09
    vertre
    -1.09
    middag
    -1.07
    Nummer
    -1.07
    POSITIVE LOGITS
     how
    1.49
     our
    1.48
     rate
    1.35
     where
    1.32
     increase
    1.30
     even
    1.24
     %
    1.23
     level
    1.23
     this
    1.20
     my
    1.20
    Activations Density 0.003%

    No Known Activations