© 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. 25816
    Prev
    Next
    INDEX
    Explanations

    regions and districts

    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
    embols
    -1.00
     család
    -0.94
    「
    -0.92
     gethan
    -0.91
     őket
    -0.89
     poliester
    -0.88
     szabály
    -0.88
     iconst
    -0.87
    αυ
    -0.87
    様でした
    -0.86
    POSITIVE LOGITS
     convenient
    1.19
     offices
    1.19
     région
    1.11
     office
    1.02
     location
    0.95
     nearer
    0.93
     region
    0.93
     regional
    0.91
    office
    0.91
    regional
    0.90
    Activations Density 0.071%

    No Known Activations