Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 6977
    Prev
    Next
    INDEX
    Explanations

    noun-phrase pairings

    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_40_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
    วาง
    0.29
     davon
    0.23
     d
    0.21
     stylized
    0.21
     Libr
    0.21
     صندوق
    0.21
     пи
    0.21
    ந்த
    0.21
    рованной
    0.20
     Myl
    0.20
    POSITIVE LOGITS
     $=$
    0.25
     schme
    0.24
    জানা
    0.24
    𒁲
    0.23
     అంటున్నారు
    0.23
    。\
    0.23
     遊ん
    0.23
     $=\
    0.23
     思っ
    0.23
    អ៊ី
    0.22
    Activations Density 0.583%

    No Known Activations