© 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. 100511
    Prev
    Next
    INDEX
    Explanations

    until now

    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
     when
    -1.68
     these
    -1.63
     Terkait
    -1.59
     Tanpa
    -1.52
     with
    -1.51
     irmã
    -1.48
    结束后
    -1.45
     both
    -1.44
    訝
    -1.42
    raujo
    -1.38
    POSITIVE LOGITS
    '
    1.81
    为止
    1.59
    
    1.56
     saludables
    1.53
    +"&
    1.51
     perfectos
    1.45
     bisher
    1.45
     conocidos
    1.42
    の人生
    1.38
    踊り
    1.37
    Activations Density 0.053%

    No Known Activations