© 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. 2987
    Prev
    Next
    INDEX
    Explanations

    mail and mailbox

    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
     موس
    -0.76
    ungle
    -0.75
    τσι
    -0.72
    горит
    -0.71
     preescolar
    -0.69
    badah
    -0.68
     doká
    -0.67
    organe
    -0.66
     chaînes
    -0.66
    yog
    -0.65
    POSITIVE LOGITS
     mailbox
    5.22
    mailbox
    3.75
    Mailbox
    3.38
     mail
    3.34
     Mail
    3.02
     inbox
    2.73
    Mail
    2.56
     MAIL
    2.50
    mail
    2.38
    邮箱
    2.33
    Activations Density 0.057%

    No Known Activations