© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68455
    Prev
    Next
    INDEX
    Explanations

    public class members

    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
     dwóch
    -1.17
     complementa
    -1.10
     continúas
    -1.10
     enju
    -1.09
     arī
    -1.09
     verdadeiro
    -1.07
    みたいに
    -1.07
     několika
    -1.06
     Vám
    -1.05
    baikan
    -1.05
    POSITIVE LOGITS
    as
    1.33
    isé
    1.19
    but
    1.18
    to
    1.18
     slechts
    1.17
     frigo
    1.13
     droog
    1.13
     zand
    1.11
     رژ
    1.11
    fore
    1.11
    Activations Density 0.016%

    No Known Activations