© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3721
    Prev
    Next
    INDEX
    Explanations

    street names and locations

    np_acts-logits-general · gemini-2.5-flash-lite

    Star Wars reference, hands, traction, complex structures, software, common, labor, photography instructor, scientists, led

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    мі
    0.21
    르
    0.21
    б
    0.20
    𝒕
    0.20
    さまざまな
    0.19
    ОР
    0.18
    НЫ
    0.18
    त्त
    0.18
    𝐼
    0.18
    mäß
    0.18
    POSITIVE LOGITS
     Blvd
    0.21
     to
    0.20
     Jamboree
    0.19
     Research
    0.19
     Central
    0.19
     with
    0.19
     Cancer
    0.19
     Orchid
    0.19
     Midlands
    0.19
     Extreme
    0.18
    Activations Density 2.137%

    No Known Activations