© 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. 7309
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
     of
    -1.94
    Mereka
    -1.68
     Typically
    -1.53
     Recently
    -1.52
    0
    -1.46
     Mereka
    -1.43
    Válasz
    -1.43
     jednak
    -1.43
     Through
    -1.43
     setelah
    -1.43
    POSITIVE LOGITS
    糨
    1.54
    viembre
    1.50
     condicionado
    1.46
     dispuesto
    1.45
     preocupado
    1.39
    исленность
    1.36
     rodo
    1.35
    weeney
    1.34
    })}$
    1.34
     ”
    1.34
    Activations Density 0.140%

    No Known Activations