© 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. 76573
    Prev
    Next
    INDEX
    Explanations

    drafting and selecting

    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
    られた
    -0.79
    塀
    -0.78
    Bail
    -0.76
     זיך
    -0.75
     lumin
    -0.75
     Landsat
    -0.74
    HDC
    -0.73
    핫
    -0.73
    ລ
    -0.73
    хня
    -0.72
    POSITIVE LOGITS
    BPA
    1.14
     BPA
    1.12
     consensus
    0.97
     projection
    0.97
     value
    0.94
     projecting
    0.91
    Selecting
    0.90
    Rounds
    0.88
     drafting
    0.88
     selecting
    0.82
    Activations Density 0.027%

    No Known Activations