© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 703
    Prev
    Next
    INDEX
    Explanations

    providing factual information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    1.00
     be
    0.84
    ä
    0.75
    \
    0.64
    ö
    0.63
     but
    0.63
    _{
    0.62
    с
    0.62
     in
    0.61
     so
    0.58
    POSITIVE LOGITS
    i
    0.71
    ي
    0.61
    헹
    0.60
     exemplaires
    0.59
     Consultado
    0.59
     rameaux
    0.59
    r
    0.59
     conclu
    0.58
     anciens
    0.58
     envoyer
    0.58
    Activations Density 5.272%

    No Known Activations