© 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. 93267
    Prev
    Next
    INDEX
    Explanations

    time stamps and numbers

    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
     in
    -1.67
     for
    -1.56
     as
    -1.35
     without
    -1.34
     this
    -1.19
     other
    -1.19
     at
    -1.18
     of
    -1.16
     if
    -1.13
     RECOMM
    -1.13
    POSITIVE LOGITS
     máme
    1.43
     cubierto
    1.38
     skvě
    1.34
     encender
    1.34
     özellikleri
    1.34
     těch
    1.33
     zajíma
    1.33
     dáms
    1.33
     rempli
    1.32
     zimní
    1.31
    Activations Density 0.001%

    No Known Activations