© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90680
    Prev
    Next
    INDEX
    Explanations

    medieval origins, baud rate, local landowners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ์
    0.50
    i
    0.49
    ни
    0.48
    ؐ
    0.47
    immersive
    0.46
    шит
    0.46
    Reconnect
    0.45
    p
    0.45
    нак
    0.44
    раст
    0.44
    POSITIVE LOGITS
     Surveyor
    0.41
    其他
    0.39
     قطع
    0.39
    0.37
    滀
    0.37
    ジア
    0.36
    滃
    0.36
    okia
    0.36
     Bibliothe
    0.35
    ตัด
    0.35
    Activations Density 0.001%

    No Known Activations