© 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. 25732
    Prev
    Next
    INDEX
    Explanations

    mid, middle, halfway

    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
     during
    -0.90
    最後まで
    -0.87
    -0.86
    umacher
    -0.74
    ⏭
    -0.74
    gó
    -0.70
    ensacola
    -0.69
    hurst
    -0.68
    ЧЕСКИ
    -0.68
     mornings
    -0.68
    POSITIVE LOGITS
     midpoint
    4.03
     mid
    3.86
    mid
    3.33
     midway
    3.17
    Mid
    2.88
     middle
    2.72
     halfway
    2.70
     Mid
    2.45
     середи
    2.39
     Midway
    2.34
    Activations Density 0.055%

    No Known Activations