© 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. 68007
    Prev
    Next
    INDEX
    Explanations

    photo credits, names, and sources

    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
     bénéfices
    -1.36
    Ĝ
    -1.24
    новая
    -1.24
     préférences
    -1.20
     prochaines
    -1.20
     THAN
    -1.17
     cementerio
    -1.16
     enten
    -1.16
    ácidos
    -1.16
    
    -1.15
    POSITIVE LOGITS
     their
    1.54
    他們
    1.39
    They
    1.37
    But
    1.35
     them
    1.34
     but
    1.34
     mereka
    1.34
     different
    1.28
    他们
    1.26
    just
    1.23
    Activations Density 0.035%

    No Known Activations