© 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. 44413
    Prev
    Next
    INDEX
    Explanations

    animals and place names

    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
    In
    -2.78
    Of
    -2.59
    
    -2.58
    7
    -2.33
    2
    -2.28
    If
    -2.27
    4
    -2.20
    V
    -2.20
    6
    -2.14
    up
    -2.11
    POSITIVE LOGITS
     ‘‘
    2.08
    muebles
    1.99
    柺
    1.89
     inspiradoras
    1.84
     considerados
    1.84
     caros
    1.81
    的核心
    1.80
     andet
    1.79
    
    1.77
    それと
    1.75
    Activations Density 0.010%

    No Known Activations