© 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. 113717
    Prev
    Next
    INDEX
    Explanations

    so that/as to

    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
    ’:
    -1.92
     tartalomajánló
    -1.74
     Bà
    -1.71
     получает
    -1.70
     करके
    -1.70
    νονται
    -1.67
    ⎘
    -1.65
    骓
    -1.64
    嚀
    -1.64
     вернуться
    -1.64
    POSITIVE LOGITS
     that
    2.44
     is
    2.02
     It
    1.97
     pertinentes
    1.80
    之为
    1.77
     to
    1.76
    th
    1.73
    o
    1.68
    as
    1.66
     bekom
    1.61
    Activations Density 0.032%

    No Known Activations