© 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. 113499
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by lowercase word

    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
    )$
    -1.63
    の種類
    -1.52
     felizes
    -1.43
    让他们
    -1.41
    uminense
    -1.40
    '
    -1.39
     sienten
    -1.37
    юра
    -1.36
     inserire
    -1.36
     Jumlah
    -1.34
    POSITIVE LOGITS
     and
    3.55
     who
    1.82
    </h1>
    1.58
    
    1.48
    from
    1.41
    stacle
    1.37
     numai
    1.34
    极了
    1.34
     will
    1.30
     contesto
    1.28
    Activations Density 0.058%

    No Known Activations