© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110491
    Prev
    Next
    INDEX
    Explanations

    names of famous people

    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
    //
    -2.08
     or
    -2.02
     /
    -1.90
     these
    -1.73
     our
    -1.70
     this
    -1.59
    ".
    -1.59
     such
    -1.58
     unserer
    -1.53
     is
    -1.51
    POSITIVE LOGITS
     koniec
    1.66
    
    1.61
     Ș
    1.60
    蚰
    1.56
     réponses
    1.56
    ǃ
    1.55
    ⚣
    1.52
     parede
    1.48
     État
    1.47
     kto
    1.46
    Activations Density 0.044%

    No Known Activations