© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71321
    Prev
    Next
    INDEX
    Explanations

    kidding sherlock

    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
    begin
    -1.87
     $
    -1.79
     to
    -1.72
    ⢅
    -1.59
     \&
    -1.52
    躂
    -1.49
     "
    -1.46
    
    -1.43
    ⚥
    -1.43
     $\
    -1.42
    POSITIVE LOGITS
     aproveitar
    1.58
     baza
    1.52
     vass
    1.42
     schlafen
    1.39
     lembrar
    1.39
    髏
    1.37
    They
    1.37
     imat
    1.35
     osc
    1.34
     osm
    1.34
    Activations Density 0.011%

    No Known Activations