© 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. 129095
    Prev
    Next
    INDEX
    Explanations

    code structure and function calls

    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
     for
    -1.70
     as
    -1.55
     while
    -1.53
     one
    -1.48
     there
    -1.45
     most
    -1.38
     other
    -1.37
     only
    -1.34
     just
    -1.29
     on
    -1.28
    POSITIVE LOGITS
     trám
    1.38
    あぁ
    1.29
     délais
    1.27
     carburant
    1.27
     imprimer
    1.26
    こない
    1.24
    つづく
    1.22
    voyer
    1.21
    凄く
    1.21
    えっ
    1.20
    Activations Density 0.040%

    No Known Activations