© 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. 15142
    Prev
    Next
    INDEX
    Explanations

    exploit, abuse or endanger

    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
    ய்டா
    0.43
    țele
    0.38
    ycopg
    0.38
     dictator
    0.38
     lexic
    0.38
    ด้วย
    0.38
    Churn
    0.37
    도
    0.37
    ồm
    0.37
    জীব
    0.36
    POSITIVE LOGITS
     overuse
    0.43
     käyttö
    0.41
    消耗
    0.41
     sillonné
    0.40
     upotre
    0.40
     usan
    0.40
     használ
    0.39
     употреб
    0.38
     =[
    0.38
     tap
    0.38
    Activations Density 0.025%

    No Known Activations