© 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. 10-GEMMASCOPE-RES-131K
    7. 43916
    Prev
    Next
    INDEX
    Explanations

    help wanted for

    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
    چک
    -1.32
    踯
    -1.28
    髫
    -1.27
    Harga
    -1.27
     lavander
    -1.25
    bases
    -1.23
    蹀
    -1.23
     broder
    -1.23
     citer
    -1.21
    PickerController
    -1.21
    POSITIVE LOGITS
     such
    1.84
     two
    1.43
     are
    1.42
     his
    1.37
     know
    1.34
     have
    1.33
     will
    1.25
     специалисты
    1.23
     see
    1.23
     Unterschied
    1.20
    Activations Density 0.024%

    No Known Activations