© 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. 100537
    Prev
    Next
    INDEX
    Explanations

    simpson and other surnames

    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
    轳
    -2.66
    で
    -2.56
    asanjo
    -2.55
    ?"
    -2.52
    。
    -2.50
    ：
    -2.47
    勠
    -2.42
    ."
    -2.41
    ('
    -2.41
     have
    -2.41
    POSITIVE LOGITS
    the
    2.88
    躄
    2.45
    垟
    2.39
     budú
    2.33
    玊
    2.31
    顽
    2.28
    鲩
    2.27
     zví
    2.25
     continúas
    2.25
     localizar
    2.23
    Activations Density 0.001%

    No Known Activations