© 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. 34-GEMMASCOPE-RES-131K
    7. 93074
    Prev
    Next
    INDEX
    Explanations

    email address

    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_34/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
    缪
    -0.77
     tfsi
    -0.77
     alamy
    -0.75
     octa
    -0.72
    тное
    -0.71
    琊
    -0.70
    新幹線
    -0.69
     allowance
    -0.68
     fuß
    -0.67
     Voiture
    -0.67
    POSITIVE LOGITS
    mail
    2.11
     mail
    2.03
    Mail
    1.73
     Mail
    1.66
     mails
    1.61
     MAIL
    1.37
    mails
    1.36
    MAIL
    1.31
    メール
    1.10
    address
    1.05
    Activations Density 0.024%

    No Known Activations