© 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. 33975
    Prev
    Next
    INDEX
    Explanations

    foreign words and code

    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
    #%%
    -1.45
     only
    -1.22
     tikai
    -1.13
    ,
    -1.13
     for
    -1.10
     everything
    -1.09
     know
    -1.08
     our
    -1.08
     these
    -1.08
     one
    -1.04
    POSITIVE LOGITS
     ihrer
    1.29
    выми
    1.23
     faciliter
    1.21
     magnifique
    1.19
     mélang
    1.18
    льники
    1.16
    ISupport
    1.16
     deras
    1.14
     delicioso
    1.13
    atique
    1.13
    Activations Density 0.018%

    No Known Activations