© 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. 71762
    Prev
    Next
    INDEX
    Explanations

    questions and definitions

    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
     реально
    -1.43
    
    -1.40
    
    -1.38
    ⼿
    -1.36
     imidlertid
    -1.34
     erforder
    -1.34
     PERSONS
    -1.34
     творо
    -1.30
     noblesse
    -1.29
     APPELLANT
    -1.27
    POSITIVE LOGITS
     we
    1.86
     what
    1.78
     things
    1.42
     people
    1.41
     which
    1.40
     possui
    1.27
    ！！！！
    1.26
     can
    1.24
     also
    1.23
     something
    1.23
    Activations Density 0.160%

    No Known Activations