© 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. 26746
    Prev
    Next
    INDEX
    Explanations

    animal's arrival

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

    needs to

    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
    кси
    0.43
    两个人
    0.43
    ającej
    0.43
    рат
    0.43
    ровой
    0.43
    жной
    0.42
    专门
    0.42
    <0xE3>
    0.40
    óc
    0.40
    ợp
    0.40
    POSITIVE LOGITS
     unavailability
    0.52
     milliseconds
    0.52
     unethical
    0.52
     macarons
    0.52
     beetroot
    0.50
     realice
    0.49
     ruining
    0.48
     blotting
    0.48
     lavender
    0.47
     utensils
    0.47
    Activations Density 0.000%

    No Known Activations