© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111763
    Prev
    Next
    INDEX
    Explanations

    provide you with

    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
    啣
    -2.20
     prakty
    -1.80
     inclut
    -1.74
    峩
    -1.73
    齮
    -1.72
    actéristi
    -1.71
    場に
    -1.70
    茈
    -1.70
    ጢ
    -1.67
    
    -1.66
    POSITIVE LOGITS
     of
    2.03
    ;
    1.80
    ,
    1.80
    Nuestro
    1.77
    Aunque
    1.76
    when
    1.74
    Además
    1.73
    Después
    1.73
    También
    1.68
    THERE
    1.68
    Activations Density 0.013%

    No Known Activations