© 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. 105798
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units like cc, % or mAh

    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
     is
    -2.45
     tienen
    -1.84
    </b>
    -1.79
     
    -1.74
    ）：
    -1.73
    》，
    -1.73
     has
    -1.69
     by
    -1.66
    ：[
    -1.66
    :「
    -1.63
    POSITIVE LOGITS
    ₶
    2.03
    nd
    2.00
    u
    1.95
    岁的
    1.75
    豳
    1.74
    </h3>
    1.73
    ts
    1.72
     ২০
    1.71
    狃
    1.66
    喟
    1.65
    Activations Density 0.014%

    No Known Activations