© 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. 74972
    Prev
    Next
    INDEX
    Explanations

    numbers and letters

    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
     vela
    -1.62
     plafon
    -1.53
     ministra
    -1.48
     fré
    -1.47
     fusil
    -1.39
     guir
    -1.38
     tré
    -1.35
     vernis
    -1.34
     igre
    -1.33
     ciment
    -1.32
    POSITIVE LOGITS
     многие
    1.32
    再去
    1.15
    (!_
    1.12
    N
    1.10
    ;,
    1.08
    7
    1.06
    C
    1.06
     posesión
    1.05
    B
    1.05
     aprendizagem
    1.05
    Activations Density 0.007%

    No Known Activations