© 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. 34730
    Prev
    Next
    INDEX
    Explanations

    amid or during

    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
    douard
    -0.77
    cap
    -0.74
    ds
    -0.73
     elit
    -0.72
    tis
    -0.70
    ཉ
    -0.70
    いかがでしたか
    -0.70
    atification
    -0.69
    tismo
    -0.69
     alleine
    -0.69
    POSITIVE LOGITS
     amid
    6.13
     amidst
    5.53
     Amid
    5.19
    Amid
    4.94
    amid
    4.81
     midst
    4.44
     وسط
    2.81
     giữa
    1.84
     tengah
    1.73
     фоне
    1.70
    Activations Density 0.163%

    No Known Activations