© 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. 102545
    Prev
    Next
    INDEX
    Explanations

    furniture storage

    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
    阄
    -1.66
    砹
    -1.48
     नए
    -1.45
     现代
    -1.45
     marinho
    -1.45
     辣
    -1.45
     Acesso
    -1.43
     台灣
    -1.42
    ဳ
    -1.41
    呿
    -1.41
    POSITIVE LOGITS
     muebles
    2.05
     ‘
    1.84
     we
    1.71
    </u>
    1.71
    with
    1.63
     others
    1.59
     avec
    1.57
    酲
    1.56
     wykor
    1.52
     الرئيسية
    1.52
    Activations Density 0.017%

    No Known Activations