© 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. 34-GEMMASCOPE-RES-131K
    4. 119188
    Prev
    Next
    INDEX
    Explanations

    class 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_34/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
    :
    -2.03
    ;
    -1.88
     like
    -1.29
    ).
    -1.24
     (
    -1.20
     as
    -1.20
     [];
    -1.14
    ??
    -1.09
    ();
    -1.03
     '';
    -1.02
    POSITIVE LOGITS
     cuna
    1.04
     >",
    1.01
     hoort
    1.00
     можем
    1.00
     {
    
    0.99
     @"/
    0.99
     vergeten
    0.98
     contrase
    0.95
     gesteld
    0.95
    、“
    0.94
    Activations Density 0.014%

    No Known Activations