© 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. 99068
    Prev
    Next
    INDEX
    Explanations

    famous people's names

    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
    了吧
    -1.70
    ".
    -1.64
    
    -1.55
    ser
    -1.47
     que
    -1.45
    now
    -1.44
     ambayo
    -1.42
     of
    -1.41
    sibile
    -1.41
     or
    -1.39
    POSITIVE LOGITS
    Один
    1.61
    捗
    1.59
     supermercado
    1.51
    Sú
    1.50
    Dá
    1.47
    Dengan
    1.46
     vinho
    1.44
     clicar
    1.43
     одного
    1.42
    悵
    1.42
    Activations Density 0.011%

    No Known Activations