© 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. 127728
    Prev
    Next
    INDEX
    Explanations

    differ from

    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
     it
    -1.74
     ehemalige
    -1.33
     including
    -1.27
     prowadzi
    -1.23
    当時は
    -1.19
    亙
    -1.19
     Pläne
    -1.18
    噐
    -1.15
    ៚
    -1.14
     same
    -1.12
    POSITIVE LOGITS
     or
    1.54
     ['$
    1.18
     embarazada
    1.13
    Breadcrumb
    1.09
    СКА
    1.09
    的身份
    1.09
     circumstances
    1.08
    편
    1.08
     to
    1.08
     season
    1.07
    Activations Density 0.454%

    No Known Activations