© 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. 113605
    Prev
    Next
    INDEX
    Explanations

    functionality and features

    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
     bazı
    -1.99
     Daß
    -1.81
     pokud
    -1.79
    Therefore
    -1.74
     Pokud
    -1.70
     Años
    -1.69
    tarjeta
    -1.68
     Portanto
    -1.68
     nedenle
    -1.63
     étn
    -1.63
    POSITIVE LOGITS
     your
    3.42
     with
    2.25
     also
    2.02
     both
    2.00
     even
    1.96
     all
    1.90
     of
    1.84
     without
    1.78
     always
    1.72
     as
    1.70
    Activations Density 0.336%

    No Known Activations