© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67976
    Prev
    Next
    INDEX
    Explanations

    preview

    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
    ),
    -2.00
     Bekannt
    -1.88
    vignon
    -1.79
     pequeña
    -1.70
    %;
    
    -1.68
    caler
    -1.66
     elegir
    -1.64
    エット
    -1.63
     Vielleicht
    -1.61
     '/':
    -1.60
    POSITIVE LOGITS
    苼
    1.86
    葙
    1.82
     the
    1.81
    v
    1.77
     of
    1.77
     cojín
    1.70
    Hermoso
    1.56
    方がいい
    1.55
     放題
    1.55
    z
    1.55
    Activations Density 0.007%

    No Known Activations