© 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. 34-GEMMASCOPE-RES-131K
    7. 78584
    Prev
    Next
    INDEX
    Explanations

    story highlights

    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_34/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
    arrón
    -0.87
     Brasília
    -0.82
    рона
    -0.78
    AID
    -0.76
    服务
    -0.75
    StackTrace
    -0.73
    넓
    -0.72
     vastaan
    -0.72
    生命
    -0.72
    acción
    -0.72
    POSITIVE LOGITS
    continues
    0.96
     публика
    0.84
     stí
    0.80
    continu
    0.77
     nods
    0.77
     complicaciones
    0.74
     bajas
    0.74
     feier
    0.73
    licit
    0.73
     验证
    0.73
    Activations Density 0.008%

    No Known Activations