© 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. 34535
    Prev
    Next
    INDEX
    Explanations

    development of

    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
     că
    -0.96
     katk
    -0.96
     reuniones
    -0.96
    amerikanischer
    -0.94
     undecided
    -0.93
     honneur
    -0.93
     parfois
    -0.93
    ֱ
    -0.92
    IfExists
    -0.92
     後
    -0.90
    POSITIVE LOGITS
     develop
    1.45
     develops
    1.40
     for
    1.22
     developed
    1.16
    developed
    1.13
     a
    1.12
     with
    1.10
     mengembangkan
    1.09
    develop
    1.09
     Develop
    1.09
    Activations Density 0.143%

    No Known Activations