© 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. 26486
    Prev
    Next
    INDEX
    Explanations

    useful items and concepts

    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
     sukienka
    -1.26
    ramide
    -1.25
    complished
    -1.15
     всичко
    -1.13
    我們
    -1.12
    şk
    -1.11
     Erweiter
    -1.10
     with
    -1.07
    gister
    -1.07
     Bildern
    -1.05
    POSITIVE LOGITS
     useful
    1.70
     usefulness
    1.69
     invaluable
    1.44
    convenience
    1.36
     use
    1.36
     help
    1.34
     tool
    1.33
     saves
    1.32
     utility
    1.30
     indispensable
    1.30
    Activations Density 0.054%

    No Known Activations