© 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. 72596
    Prev
    Next
    INDEX
    Explanations

    symbolic: memory, traits, gesture, metaphor

    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
    ↵
    -4.09
     The
    -3.69
     
    -2.81
     (
    -2.58
    3
    -2.53
     â
    -2.41
     FROM
    -2.36
      
    -2.34
     $
    -2.30
    里有
    -2.30
    POSITIVE LOGITS
    
    3.52
    ൎ
    3.38
    ꔹ
    2.94
     殼
    2.88
    ỽ
    2.77
     内衣
    2.73
     processi
    2.70
     CITIES
    2.69
     wijze
    2.64
    
    2.64
    Activations Density 0.001%

    No Known Activations