© 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. 31-GEMMASCOPE-2-RES-262K
    7. 44682
    Prev
    Next
    INDEX
    Explanations

    citations and footnotes

    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
    \
    0.41
    িগ
    0.41
     των
    0.40
    рон
    0.38
     \
    0.37
    胝
    0.37
     које
    0.36
    amento
    0.36
    esa
    0.36
    犮
    0.35
    POSITIVE LOGITS
     حفظ
    0.40
     inhale
    0.40
     subconsciously
    0.39
     dipped
    0.38
     anschließend
    0.38
     bewusst
    0.38
     handheld
    0.37
    ตะ
    0.37
    ók
    0.37
    কেমিক্যাল
    0.37
    Activations Density 0.001%

    No Known Activations