© 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. 25125
    Prev
    Next
    INDEX
    Explanations

    bread crumbs

    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
     gedeelte
    -1.13
    んですけど
    -0.98
     Isto
    -0.98
    骶
    -0.98
    ulele
    -0.97
     hígado
    -0.96
     afectadas
    -0.96
     navires
    -0.94
    Bav
    -0.94
     disfru
    -0.94
    POSITIVE LOGITS
     also
    1.77
     should
    1.50
     others
    1.41
     will
    1.38
     other
    1.31
     if
    1.30
     you
    1.22
     to
    1.16
     must
    1.14
     avoid
    1.12
    Activations Density 0.022%

    No Known Activations