© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99394
    Prev
    Next
    INDEX
    Explanations

    mailing and prices

    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
    itrile
    -0.90
    𝚎
    -0.88
     bermain
    -0.83
     archived
    -0.82
    bahnhof
    -0.81
     https
    -0.81
    Link
    -0.77
    旁边
    -0.77
     LINK
    -0.77
    
    -0.77
    POSITIVE LOGITS
     postage
    1.46
     postal
    1.45
     enclose
    1.43
     mail
    1.42
     mailing
    1.41
     Send
    1.23
     send
    1.23
     mailed
    1.20
     addresses
    1.19
     orders
    1.13
    Activations Density 0.026%

    No Known Activations