© 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. 63751
    Prev
    Next
    INDEX
    Explanations

    delivery destinations

    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
    ([]);
    -0.88
     offerings
    -0.86
     incoming
    -0.85
     visiting
    -0.84
     withdrawal
    -0.83
    AYE
    -0.79
     quirúrg
    -0.79
    ょ
    -0.79
    RATING
    -0.78
     momentary
    -0.76
    POSITIVE LOGITS
     doorstep
    1.46
     address
    1.45
     door
    1.41
     destinations
    1.41
     destination
    1.41
    指定
    1.40
     addresses
    1.37
     specified
    1.36
     адре
    1.35
     homes
    1.34
    Activations Density 0.038%

    No Known Activations