© 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. 71417
    Prev
    Next
    INDEX
    Explanations

    of a number

    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
     both
    -2.02
     but
    -1.99
     and
    -1.92
     a
    -1.72
     either
    -1.71
    </i>
    -1.70
    to
    -1.70
     επίσης
    -1.66
     same
    -1.64
     respective
    -1.63
    POSITIVE LOGITS
     them
    2.11
    einer
    1.90
     lü
    1.84
     parfü
    1.84
    Selamat
    1.84
     buhay
    1.82
    wurde
    1.81
    Wady
    1.81
     akrab
    1.80
    unser
    1.79
    Activations Density 0.016%

    No Known Activations