© 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. 73890
    Prev
    Next
    INDEX
    Explanations

    package structure; names like James Bopp

    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
    s
    -1.96
     to
    -1.86
    nitř
    -1.61
        
    -1.53
     Either
    -1.48
    珦
    -1.48
     ebenfalls
    -1.46
     of
    -1.45
     Once
    -1.44
    pantalón
    -1.43
    POSITIVE LOGITS
    และ
    1.95
     and
    1.92
    หรือ
    1.77
     kalori
    1.62
    蔸
    1.59
    饜
    1.50
     یا
    1.48
    ANCIAL
    1.44
    passengers
    1.44
    endaten
    1.43
    Activations Density 0.003%

    No Known Activations