© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43663
    Prev
    Next
    INDEX
    Explanations

    physical components, units, or parts

    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
     and
    -1.41
     different
    -1.38
     also
    -1.30
     twofold
    -1.30
     again
    -1.29
     part
    -1.25
    1
    -1.22
     too
    -1.20
     already
    -1.20
     &
    -1.19
    POSITIVE LOGITS
    nością
    1.62
    orice
    1.47
    rmızı
    1.44
    鳚
    1.44
     особенно
    1.41
    antism
    1.34
    ﻝ
    1.34
    Ϫ
    1.33
    🢒
    1.33
    שלום
    1.33
    Activations Density 0.151%

    No Known Activations