© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104187
    Prev
    Next
    INDEX
    Explanations

    military veterans and markets

    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
    所在的
    -1.77
    inerario
    -1.66
    かれて
    -1.47
    ニメ
    -1.46
    ᷇
    -1.45
    parseLong
    -1.43
    orghini
    -1.41
    ῎
    -1.39
    dersfield
    -1.38
    自身的
    -1.38
    POSITIVE LOGITS
    in
    1.67
     where
    1.63
    and
    1.60
    i
    1.54
    取得
    1.53
    "
    1.46
    ”,
    1.45
    ka
    1.42
    will
    1.37
    </h3>
    1.36
    Activations Density 0.030%

    No Known Activations