© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45186
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities

    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_10/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
    珺
    -1.47
     bygge
    -1.45
     torsdag
    -1.44
     them
    -1.34
     tå
    -1.30
     dziecię
    -1.25
     fredag
    -1.21
     onsdag
    -1.21
     ungdom
    -1.20
     natten
    -1.20
    POSITIVE LOGITS
     this
    1.88
     such
    1.38
     these
    1.31
     Če
    1.27
     which
    1.24
     since
    1.24
     if
    1.19
     our
    1.11
     should
    1.09
     because
    1.09
    Activations Density 0.339%

    No Known Activations