© 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. 15393
    Prev
    Next
    INDEX
    Explanations

    code block structures

    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
     suscit
    -1.23
     teneur
    -1.20
     unrivalled
    -1.19
     sorgfäl
    -1.19
    костюм
    -1.16
     sigui
    -1.15
     Administr
    -1.15
    撸
    -1.11
     皮肤
    -1.11
    参见
    -1.10
    POSITIVE LOGITS
     activities
    1.30
     and
    1.29
     items
    1.28
     products
    1.27
     tasks
    1.25
    !!!!!!
    1.25
     animals
    1.23
     what
    1.20
    alties
    1.20
     services
    1.19
    Activations Density 0.065%

    No Known Activations