© 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. 34-GEMMASCOPE-RES-131K
    7. 50202
    Prev
    Next
    INDEX
    Explanations

    code module and error

    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
    Ingredientes
    -0.80
    스터
    -0.77
    strokeColor
    -0.77
    colato
    -0.76
    IMIENTO
    -0.75
     радиа
    -0.75
    inkov
    -0.73
    تس
    -0.73
    llus
    -0.73
    高中
    -0.73
    POSITIVE LOGITS
    未満
    0.83
    イヤー
    0.76
    فاق
    0.76
     Psychol
    0.73
     Morena
    0.72
    所有人
    0.72
     マグ
    0.71
     ويع
    0.71
     Caw
    0.71
     herbaceous
    0.71
    Activations Density 0.002%

    No Known Activations