© 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. 85592
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     sandero
    -1.39
     qashqai
    -1.39
    踅
    -1.36
     angelo
    -1.34
     borse
    -1.32
     milano
    -1.32
     piaggio
    -1.32
     aquarelle
    -1.30
     maroc
    -1.30
     fuo
    -1.30
    POSITIVE LOGITS
    0
    1.61
     выбира
    1.22
     "
    1.13
    自己
    1.10
     [],
    1.09
     다
    1.06
    choose
    1.05
     if
    1.04
     he
    1.02
    ές
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.