© 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. 10-GEMMASCOPE-RES-131K
    4. 123989
    Prev
    Next
    INDEX
    Explanations

    on behalf of

    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_10/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
     some
    -1.70
     about
    -1.61
     Ländern
    -1.55
     When
    -1.51
     älteren
    -1.46
     only
    -1.40
    Some
    -1.38
     three
    -1.36
     two
    -1.36
     when
    -1.36
    POSITIVE LOGITS
     kazak
    1.70
     of
    1.61
     cordoba
    1.48
    
    1.47
     optik
    1.45
     rapor
    1.43
    😺
    1.42
     intrig
    1.41
     மற்றும்
    1.39
     sâ
    1.39
    Activations Density 0.030%

    No Known Activations