© 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. 39760
    Prev
    Next
    INDEX
    Explanations

    surnames and place names

    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
    猻
    -3.73
    饜
    -3.28
     they
    -3.27
    k
    -3.03
    慙
    -2.91
    ﮕ
    -2.89
    ar
    -2.86
    y
    -2.83
     nahil
    -2.69
    鲧
    -2.69
    POSITIVE LOGITS
    ୌ
    2.36
     Both
    2.36
     schützen
    2.34
    akterysty
    2.33
    ;
    2.31
     They
    2.31
     توسط
    2.25
    𓆜
    2.25
     logistical
    2.23
     cortesía
    2.22
    Activations Density 0.004%

    No Known Activations