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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 36503
    Prev
    Next
    INDEX
    Explanations

    check, propose, and exact circumstances

    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_65k_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
    يد
    0.51
    ו
    0.49
    強度
    0.48
    利
    0.46
    統合
    0.46
    資本
    0.45
    জ
    0.45
    用戶
    0.44
    виться
    0.44
    feature
    0.44
    POSITIVE LOGITS
     soal
    0.53
     K
    0.51
     DM
    0.50
     lookout
    0.48
     Phuket
    0.48
    뻗
    0.48
     Marin
    0.47
     Munster
    0.47
     Delegates
    0.47
     prenot
    0.46
    Activations Density 0.002%

    No Known Activations