© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69105
    Prev
    Next
    INDEX
    Explanations

    types of objects and activities

    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
     as
    -1.97
     through
    -1.39
     when
    -1.38
     having
    -1.34
     in
    -1.33
     and
    -1.29
     an
    -1.28
     until
    -1.26
     Having
    -1.23
     demonstrate
    -1.22
    POSITIVE LOGITS
     autonomie
    1.27
     tromper
    1.26
     bénéficient
    1.20
     aiment
    1.20
     ſou
    1.14
     ſever
    1.14
     chiffres
    1.13
     gouttes
    1.13
     témoins
    1.13
     feux
    1.13
    Activations Density 0.070%

    No Known Activations