© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44996
    Prev
    Next
    INDEX
    Explanations

    painted turquoise, Louis Vuitton, sudden cardiac, titration

    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
     you
    -1.76
    
    -1.74
    
    -1.70
     therefore
    -1.65
    何より
    -1.59
    сторінку
    -1.55
    鸲
    -1.51
    鿬
    -1.48
     to
    -1.46
    珦
    -1.46
    POSITIVE LOGITS
     from
    2.03
     with
    1.95
    .
    1.86
     of
    1.78
     referirse
    1.48
     Despite
    1.41
     Seems
    1.41
     without
    1.39
     zawsze
    1.38
     چگونه
    1.37
    Activations Density 0.024%

    No Known Activations