© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14372
    Prev
    Next
    INDEX
    Explanations

    log level or threshold

    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
     with
    -1.15
     unique
    -1.12
     problems
    -1.09
     Unlike
    -1.05
     Specifically
    -1.02
     positive
    -0.99
     During
    -0.99
    ͛
    -0.97
     smooth
    -0.96
     Typically
    -0.96
    POSITIVE LOGITS
     beż
    1.23
    ៉
    1.14
    躄
    1.08
    tissimo
    1.06
    baca
    1.05
     vandaag
    1.02
     currentTime
    1.02
     umur
    1.02
     bescher
    1.01
    gister
    1.00
    Activations Density 0.010%

    No Known Activations