© 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. 72110
    Prev
    Next
    INDEX
    Explanations

    button actions and UI elements

    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
     informacija
    -1.18
     now
    -1.16
     because
    -1.14
    čnosti
    -1.00
     pazi
    -0.98
     of
    -0.97
     since
    -0.96
    g
    -0.94
     all
    -0.93
     $
    -0.91
    POSITIVE LOGITS
     option
    1.20
    gató
    1.16
     Option
    1.13
     Böyle
    1.05
    issez
    1.05
     beiden
    1.05
     réponse
    1.04
    Option
    1.04
     ито
    1.04
     avenir
    1.00
    Activations Density 0.011%

    No Known Activations