© 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. 56954
    Prev
    Next
    INDEX
    Explanations

    describing content or relationships

    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
    Not in Any Lists

    No Comments

    Negative Logits
     própri
    -1.46
    itself
    -1.34
    atization
    -1.25
     illustre
    -1.23
     newcomers
    -1.23
     campeón
    -1.23
     gouverneur
    -1.22
     工房
    -1.20
    翃
    -1.19
    swire
    -1.18
    POSITIVE LOGITS
     who
    2.23
     whose
    1.57
     and
    1.41
     with
    1.41
     a
    1.41
     has
    1.39
     member
    1.36
     having
    1.34
     had
    1.31
     responsible
    1.27
    Activations Density 0.078%

    No Known Activations