© 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. 128474
    Prev
    Next
    INDEX
    Explanations

    water damage repair

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

    presentation prepared

    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
    زیز
    0.49
     sétimo
    0.45
     encarg
    0.45
     verduras
    0.45
    皙
    0.44
     цилинд
    0.43
     Aujourd
    0.43
    不僅
    0.43
     pulgadas
    0.42
     refroidissement
    0.42
    POSITIVE LOGITS
     Genie
    0.51
     Diversity
    0.46
    ës
    0.45
     gee
    0.44
     Pathways
    0.43
     Myers
    0.43
    ้อ
    0.43
     Bike
    0.43
     Vote
    0.43
    >≥</
    0.42
    Activations Density 0.000%

    No Known Activations