© 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. 32806
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     just
    -1.23
     to
    -1.20
     only
    -1.18
    日を
    -1.05
    |'.'
    -1.02
     for
    -1.00
     Février
    -1.00
    lecteurs
    -0.97
     might
    -0.96
     (
    -0.96
    POSITIVE LOGITS
    municipi
    1.38
     нашел
    1.37
    Rote
    1.36
    Continu
    1.33
    Descriere
    1.32
    Vra
    1.30
    Struktur
    1.29
     olika
    1.29
    Mí
    1.27
    Torna
    1.26
    Activations Density 0.002%

    No Known Activations