© 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. 119093
    Prev
    Next
    INDEX
    Explanations

    row and column indices

    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
     admitting
    -0.78
    ще
    -0.78
    jetivo
    -0.76
     nationalists
    -0.74
    InternalFrame
    -0.72
     each
    -0.71
    εσ
    -0.70
     wholes
    -0.70
    minWidth
    -0.68
    &&(
    -0.68
    POSITIVE LOGITS
     row
    2.33
     rows
    2.33
     ROW
    1.79
    Row
    1.78
     Row
    1.66
     Rows
    1.66
    Rows
    1.61
    rows
    1.57
    ROWS
    1.57
    row
    1.55
    Activations Density 0.028%

    No Known Activations