© 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. 21344
    Prev
    Next
    INDEX
    Explanations

    Azerbaijan, xls files, cryptography

    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
     of
    -2.72
    趼
    -2.69
     容量
    -2.63
    淠
    -2.48
    阄
    -2.48
    に入れる
    -2.47
    垌
    -2.47
     ด้วย
    -2.45
     nė
    -2.44
    ㄉ
    -2.41
    POSITIVE LOGITS
    or
    2.80
    ✕
    2.50
    they
    2.47
    или
    2.47
    ский
    2.42
    </u>
    2.41
     faciliter
    2.41
     leggero
    2.34
    these
    2.33
    fully
    2.27
    Activations Density 0.005%

    No Known Activations