© 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. 34344
    Prev
    Next
    INDEX
    Explanations

    code, functions, objects

    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
     noteworthy
    -1.36
     because
    -1.33
     since
    -1.30
     osal
    -1.25
     remarkable
    -1.25
     incredible
    -1.24
     while
    -1.23
     good
    -1.23
     only
    -1.23
     people
    -1.21
    POSITIVE LOGITS
     goûts
    1.20
     vendeurs
    1.17
    -------
    1.15
     doba
    1.14
     prochaines
    1.10
    tey
    1.08
    usehen
    1.07
    ulfon
    1.05
     doivent
    1.03
    
    1.02
    Activations Density 0.012%

    No Known Activations