© 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. 10-GEMMASCOPE-RES-131K
    7. 40414
    Prev
    Next
    INDEX
    Explanations

    hypothetical scenarios and outcomes

    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_10/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
    Specifically
    -1.16
     if
    -1.16
     also
    -1.16
     especially
    -1.16
     тоже
    -1.13
    については
    -1.13
     too
    -1.08
     specifically
    -1.05
     ALSO
    -1.05
     unduly
    -1.05
    POSITIVE LOGITS
     that
    1.33
    飚
    1.22
    開始
    1.10
     بف
    1.09
     from
    1.06
     maternelle
    1.05
     اینترنتی
    1.05
     started
    1.04
     primeros
    1.03
     this
    1.01
    Activations Density 0.033%

    No Known Activations