© 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. 22-GEMMASCOPE-RES-131K
    7. 128275
    Prev
    Next
    INDEX
    Explanations

    home, visitors, top, bottom

    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
     famí
    -1.12
    蟊
    -1.10
     vair
    -1.09
    や
    -1.06
     kanyang
    -1.05
     kani
    -1.05
     vigne
    -1.05
     jego
    -1.05
     lumi
    -1.04
    😊
    -1.03
    POSITIVE LOGITS
     at
    1.25
    re
    1.09
     entrada
    1.05
     castillo
    1.02
     Perhaps
    1.01
     зберіга
    1.01
     unrelenting
    1.01
     flimsy
    1.00
     εί
    0.99
     exquisite
    0.96
    Activations Density 0.002%

    No Known Activations