© 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. 87008
    Prev
    Next
    INDEX
    Explanations

    import and context

    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
     problemów
    -0.79
    ジック
    -0.79
    ёд
    -0.78
     pikir
    -0.78
    Pens
    -0.78
    殤
    -0.78
    やすい
    -0.77
    humour
    -0.77
    údio
    -0.75
    XmlIgnore
    -0.75
    POSITIVE LOGITS
     tele
    0.90
     socket
    0.84
    Layouts
    0.83
     einsch
    0.81
     tuna
    0.80
     WK
    0.77
    ям
    0.77
     pricing
    0.77
     sen
    0.76
     papa
    0.75
    Activations Density 0.005%

    No Known Activations