© 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. 22-GEMMASCOPE-RES-131K
    7. 15815
    Prev
    Next
    INDEX
    Explanations

    car specification modifiers

    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_22/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
     توانند
    -1.22
    或
    -1.19
    labelControl
    -1.16
    meuble
    -1.14
    Cartney
    -1.13
    смарт
    -1.11
     creato
    -1.10
     themselves
    -1.09
    ועל
    -1.08
    angliski
    -1.08
    POSITIVE LOGITS
     with
    1.17
    ところに
    1.13
    tschaft
    1.02
     full
    1.02
    //});
    1.01
     chè
    1.00
     tatou
    0.98
    汙
    0.96
     extras
    0.96
     extensive
    0.93
    Activations Density 0.042%

    No Known Activations