© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33734
    Prev
    Next
    INDEX
    Explanations

    Eugene and variations

    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
    Mari
    -0.80
    ilen
    -0.79
     анд
    -0.75
    久しぶりに
    -0.75
     pequeñas
    -0.75
    titu
    -0.75
     久
    -0.73
    preuves
    -0.73
    mism
    -0.72
    を選択します
    -0.72
    POSITIVE LOGITS
     carbo
    0.81
     Kaspersky
    0.79
     henkilö
    0.77
     reconstructions
    0.77
    着一
    0.77
    għ
    0.76
    Eugen
    0.75
    ்கள
    0.74
     surrounds
    0.73
     OREGON
    0.73
    Activations Density 0.020%

    No Known Activations