© 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. 67738
    Prev
    Next
    INDEX
    Explanations

    names like Miguel, Xavier, Michel

    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
     They
    -2.84
    }$
    -2.41
    說
    -2.33
     véritable
    -2.30
     we
    -2.19
     ambayo
    -2.19
    銠
    -2.16
    就是在
    -2.09
    神
    -2.09
     verkaufen
    -2.08
    POSITIVE LOGITS
    In
    2.52
    」，
    2.48
    al
    2.38
    ’，
    2.30
    vantaged
    2.30
    ⇴
    2.27
     lyder
    2.16
    at
    2.16
     הייתה
    2.16
    इटम
    2.13
    Activations Density 0.004%

    No Known Activations