© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44931
    Prev
    Next
    INDEX
    Explanations

    numerical periods and quantities

    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
    replyreport
    -2.05
    〝
    -1.88
     網
    -1.85
    ('');
    -1.81
    ),
    -1.80
    也有
    -1.77
    Ꮉ
    -1.77
    㩒
    -1.76
     $\&$
    -1.76
    ?」
    -1.76
    POSITIVE LOGITS
    豳
    2.81
    enablog
    2.36
    邶
    2.33
     damaligen
    2.22
    嬲
    2.17
     solchen
    2.14
     Psychologie
    2.13
     Männern
    2.08
     vorigen
    2.08
    硖
    2.06
    Activations Density 0.099%

    No Known Activations