© 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. 79157
    Prev
    Next
    INDEX
    Explanations

    Wildlife Refuge, Cross Insurance

    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
     احمد
    -0.78
     Koreans
    -0.74
     Phong
    -0.73
     Caul
    -0.69
    ceive
    -0.69
     கு
    -0.68
    殤
    -0.68
    uffle
    -0.68
    rippa
    -0.68
    Scroller
    -0.68
    POSITIVE LOGITS
     Subaru
    1.55
     subaru
    1.19
    Subaru
    1.16
    SOA
    1.02
     Outback
    1.02
     Symmetric
    0.98
     Forester
    0.94
    glue
    0.88
     symmetrical
    0.85
    Symmetric
    0.85
    Activations Density 0.007%

    No Known Activations