© 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. 86907
    Prev
    Next
    INDEX
    Explanations

    viewport width=device-width

    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
    şti
    -0.81
     wcześniej
    -0.78
    шом
    -0.78
     joined
    -0.75
    قرأ
    -0.75
    ）（
    -0.74
    碍
    -0.74
     already
    -0.73
     łatwo
    -0.73
     bezpośrednio
    -0.72
    POSITIVE LOGITS
     width
    1.13
    device
    1.05
    width
    1.05
     device
    0.94
    ancho
    0.91
     Width
    0.90
     *,
    0.89
     widths
    0.89
     WIDTH
    0.89
    Width
    0.87
    Activations Density 0.008%

    No Known Activations