© 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. 40-GEMMASCOPE-2-RES-262K
    7. 7775
    Prev
    Next
    INDEX
    Explanations

    legal document phrases

    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
    น้ำ
    0.39
    ర్వాత
    0.39
     যেকোনো
    0.39
    ভারতীয়
    0.38
     بھارتی
    0.38
     গাঙ্গুল
    0.38
    ۓ
    0.38
    UnderWater
    0.38
    ஐ
    0.38
    ⴰ
    0.38
    POSITIVE LOGITS
     impug
    0.66
     Respondent
    0.53
     pleaded
    0.48
     Defendant
    0.47
     aforesaid
    0.47
     defendant
    0.45
     alleged
    0.45
     forthwith
    0.44
     undoubt
    0.44
     relied
    0.44
    Activations Density 0.004%

    No Known Activations