© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102895
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     Empirical
    -0.79
     Trek
    -0.75
    tierrez
    -0.73
     Xing
    -0.72
     Xia
    -0.71
     Deleting
    -0.71
    ifest
    -0.70
     HTTP
    -0.70
     Ryan
    -0.70
     gorro
    -0.68
    POSITIVE LOGITS
    AsString
    0.75
    zoni
    0.71
    ál
    0.71
    PopMatrix
    0.69
     ص
    0.68
     Aren
    0.67
    ignan
    0.67
    گاهی
    0.67
     Lind
    0.65
    biol
    0.65
    Activations Density 0.250%

    No Known Activations