© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128263
    Prev
    Next
    INDEX
    Explanations

    his followed by a noun

    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
    ."
    -2.55
    ↑↑↑</
    -2.42
    婞
    -2.36
    檫
    -2.34
    洐
    -2.34
    ,
    -2.33
     museu
    -2.31
    栳
    -2.28
    นี้
    -2.25
    ementara
    -2.25
    POSITIVE LOGITS
    {
    3.16
     His
    2.86
    ’
    2.66
     \
    2.59
    \
    2.55
    In
    2.53
     ‘‘
    2.42
    His
    2.28
    </h1>
    2.23
     The
    2.20
    Activations Density 0.007%

    No Known Activations