© 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. 113758
    Prev
    Next
    INDEX
    Explanations

    percentage identical

    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
    镡
    -1.88
    konzert
    -1.65
    鼕
    -1.64
     différente
    -1.53
    
    -1.53
    咈
    -1.52
     proyectos
    -1.51
     certificación
    -1.49
    糌
    -1.49
    Assemblée
    -1.48
    POSITIVE LOGITS
     for
    2.14
     when
    2.05
     while
    2.02
     on
    1.82
     because
    1.74
     due
    1.73
     during
    1.73
     despite
    1.70
     from
    1.66
     to
    1.63
    Activations Density 0.044%

    No Known Activations