© 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. 34-GEMMASCOPE-RES-131K
    7. 3269
    Prev
    Next
    INDEX
    Explanations

    HTML doctype declarations

    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_34/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
     quirky
    -1.30
     wondrous
    -1.23
     goofy
    -1.18
    鶫
    -1.18
     opulent
    -1.16
     AMERICAN
    -1.13
     astounding
    -1.13
     dreadful
    -1.12
     flamboyant
    -1.12
     quintessential
    -1.11
    POSITIVE LOGITS
     superbly
    1.41
     with
    1.27
     exquisitely
    1.19
     or
    1.18
     and
    1.16
     by
    1.16
     perpetually
    1.15
     so
    1.12
     make
    1.12
     severely
    1.11
    Activations Density 0.004%

    No Known Activations