© 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-65K
    7. 27677
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     assur
    0.52
    ême
    0.46
    傷害
    0.46
    ة
    0.46
     fighter
    0.45
     protection
    0.45
     assurance
    0.44
     Fighters
    0.44
     assurances
    0.44
     अमी
    0.43
    POSITIVE LOGITS
    üyük
    0.46
     yle
    0.46
     执行
    0.46
    ')";
    0.43
    mygray
    0.42
    ികൾ
    0.42
    leşik
    0.42
    englisch
    0.42
    piej
    0.42
     yoğun
    0.41
    Activations Density 0.006%

    No Known Activations