© 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. 27041
    Prev
    Next
    INDEX
    Explanations

    professional affiliations and roles

    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
     that
    -1.66
     then
    -1.31
     juos
    -1.19
    grees
    -1.13
     them
    -1.13
     Să
    -1.09
     by
    -1.06
     Wartawan
    -1.05
     thereafter
    -1.02
     žem
    -0.99
    POSITIVE LOGITS
    前は
    1.16
     lastly
    1.12
     civic
    1.10
     antiga
    1.09
     I
    1.09
    ื่น
    1.08
     ambiental
    1.04
     volunteer
    1.02
     aktif
    1.01
    Schwer
    1.00
    Activations Density 0.020%

    No Known Activations