© 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. 7686
    Prev
    Next
    INDEX
    Explanations

    at + place/entity

    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
     
    -2.16
    .
    -2.13
    ᥬ
    -1.95
     Another
    -1.88
     поддер
    -1.78
    γέν
    -1.73
    €“
    -1.68
     impreso
    -1.65
    题材
    -1.65
    KommentareTeilen
    -1.64
    POSITIVE LOGITS
     for
    2.28
     it
    2.19
     by
    2.17
     what
    1.99
     of
    1.94
     so
    1.92
     грудня
    1.84
     consequently
    1.81
     these
    1.77
     such
    1.77
    Activations Density 0.135%

    No Known Activations