Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 52
    Prev
    Next
    INDEX
    Explanations

    aircraft registration

    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
     ASF
    -0.79
    BIÉN
    -0.78
     prejud
    -0.75
     spazz
    -0.73
    Drivers
    -0.72
    ágok
    -0.72
     uintptr
    -0.72
     mezcla
    -0.71
     مجموعة
    -0.69
     tiers
    -0.69
    POSITIVE LOGITS
     registration
    1.80
     Registration
    1.41
    registration
    1.32
    REGISTRATION
    1.29
    Registration
    1.29
     registrations
    1.28
     REGISTRATION
    1.25
     matrícula
    1.25
     registered
    1.14
     регистра
    1.13
    Activations Density 0.023%

    No Known Activations