© 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. 7568
    Prev
    Next
    INDEX
    Explanations

    It's been a while

    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
     by
    -2.38
     to
    -2.19
     is
    -1.98
     it
    -1.91
     why
    -1.85
    colazione
    -1.78
     on
    -1.63
     are
    -1.58
     in
    -1.57
     and
    -1.52
    POSITIVE LOGITS
     trám
    1.92
     a
    1.92
    法国
    1.82
     ráp
    1.79
    賸
    1.68
     utilisés
    1.67
    ᕼ
    1.67
     fotó
    1.64
     tué
    1.63
    懨
    1.63
    Activations Density 0.014%

    No Known Activations