© 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. 44562
    Prev
    Next
    INDEX
    Explanations

    Pd, comm, кон, honda

    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
    s
    -2.91
    e
    -2.89
    鴣
    -2.73
    </h3>
    -2.72
    谖
    -2.45
    ed
    -2.42
    c
    -2.42
    ль
    -2.34
    </i>
    -2.33
    </h1>
    -2.23
    POSITIVE LOGITS
    顚
    2.77
    ⚢
    2.69
    風險
    2.64
    わたしは
    2.63
    䛗
    2.61
    ᕮ
    2.47
    좆
    2.41
    玬
    2.41
    ⢪
    2.38
     snippets
    2.34
    Activations Density 0.001%

    No Known Activations