© 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. 80904
    Prev
    Next
    INDEX
    Explanations

    names starting with Eric

    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
    akal
    -0.81
     ट
    -0.77
     thinking
    -0.77
    론
    -0.76
    ək
    -0.75
    珩
    -0.74
    DEL
    -0.74
     украшения
    -0.73
    负
    -0.73
    Gemeinsame
    -0.72
    POSITIVE LOGITS
    Jegy
    0.84
     hj
    0.74
     أيضا
    0.73
    یرات
    0.73
    Avi
    0.73
     krep
    0.73
     kano
    0.72
    青山
    0.72
     simpto
    0.71
    giatan
    0.71
    Activations Density 0.023%

    No Known Activations