© 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. 73883
    Prev
    Next
    INDEX
    Explanations

    Red meat, must only, not defined

    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
    契
    -0.79
    ării
    -0.77
    ෙ
    -0.75
    ന്
    -0.74
    зон
    -0.70
     Michael
    -0.70
    StructField
    -0.70
    боры
    -0.69
    AppState
    -0.68
     урока
    -0.68
    POSITIVE LOGITS
     山本
    0.88
     européens
    0.86
     gekommen
    0.85
     ilyen
    0.81
     gyvento
    0.80
    viens
    0.80
    兲
    0.79
    ditionally
    0.79
     located
    0.78
     etiam
    0.78
    Activations Density 0.000%

    No Known Activations