© 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. 114665
    Prev
    Next
    INDEX
    Explanations

    universities and academic programs

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

    Washington, Georgia, error

    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
    ളി
    0.40
     Insect
    0.40
    ◊
    0.40
    ulton
    0.39
    Insect
    0.39
    惱
    0.39
     founders
    0.38
     Avion
    0.37
    စိတ်အပိုင်း
    0.37
    ところに
    0.37
    POSITIVE LOGITS
     UVA
    0.40
    gt
    0.40
    IU
    0.39
    graphql
    0.39
     Uw
    0.39
    ド
    0.39
     IU
    0.39
    coroutines
    0.39
    ้ว
    0.38
    CBUUID
    0.38
    Activations Density 0.074%

    No Known Activations