© 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. 54320
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
     of
    -1.55
     they
    -1.50
     '
    -1.48
     a
    -1.44
     with
    -1.31
     "
    -1.27
     the
    -1.23
     
    -1.22
     by
    -1.20
     to
    -1.18
    POSITIVE LOGITS
     jätte
    1.25
     История
    1.21
     isolé
    1.21
     安装
    1.20
     adverten
    1.20
    брь
    1.18
    grenze
    1.17
    zaamheid
    1.16
     varmt
    1.16
    !");
    
    1.16
    Activations Density 0.007%

    No Known Activations