© 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. 80833
    Prev
    Next
    INDEX
    Explanations

    message boxes and dialogs

    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
    ANCHE
    -0.77
     балан
    -0.76
    MinValue
    -0.75
     qualsiasi
    -0.69
     implement
    -0.68
    面白かった
    -0.68
     szere
    -0.67
    압
    -0.67
    estinian
    -0.66
    raph
    -0.66
    POSITIVE LOGITS
     box
    1.64
    box
    1.46
     boxes
    1.33
     Boxes
    1.28
    BOX
    1.27
    boxes
    1.23
     Box
    1.20
    Box
    1.16
     showed
    1.09
     show
    1.00
    Activations Density 0.004%

    No Known Activations