© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 9139
    Prev
    Next
    INDEX
    Explanations

    state completion or modification

    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_16_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
    ﺮ
    0.63
    of
    0.61
    ﻚ
    0.61
    ધાનસભા
    0.60
     〢
    0.60
    ofd
    0.59
    おお
    0.59
     ı
    0.58
    ෝ
    0.57
     î
    0.57
    POSITIVE LOGITS
    ت
    1.51
    i
    1.20
    ed
    1.15
    त
    1.06
    ي
    1.05
    et
    1.04
    n
    1.02
    em
    0.99
    י
    0.99
    सँग
    0.96
    Activations Density 0.427%

    No Known Activations