© 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. 10-GEMMASCOPE-RES-131K
    7. 99780
    Prev
    Next
    INDEX
    Explanations

    packet data transmission

    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_10/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
    o
    -3.13
    h
    -3.11
    or
    -2.73
    The
    -2.55
    <em>
    -2.41
     -
    -2.31
     didn
    -2.13
    湍
    -2.11
    ne
    -2.06
    孩子
    -2.05
    POSITIVE LOGITS
    इटम
    3.03
     dañ
    2.69
    訁
    2.61
     ибо
    2.59
     erwähnten
    2.55
    ixante
    2.53
    ⇰
    2.53
    苙
    2.47
    🕡
    2.47
     учетом
    2.45
    Activations Density 0.008%

    No Known Activations