© 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. 103882
    Prev
    Next
    INDEX
    Explanations

    presentation structure

    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
    inku
    -0.84
    ܛ
    -0.83
    használ
    -0.83
    ciclop
    -0.79
     Baş
    -0.79
     hin
    -0.79
    ڏ
    -0.79
    பி
    -0.77
    பு
    -0.75
    atikan
    -0.75
    POSITIVE LOGITS
     slide
    0.98
     which
    0.88
    +='
    0.86
     αλλά
    0.85
    slide
    0.82
    pptx
    0.75
     contd
    0.75
     Tangerang
    0.75
    ָם
    0.75
    TCG
    0.74
    Activations Density 0.003%

    No Known Activations