© 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. 170088
    Prev
    Next
    INDEX
    Explanations

    describing states or limitations

    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
    စိတ်
    0.44
    judicial
    0.44
     funcionarios
    0.44
    ίνουν
    0.43
    preneurs
    0.43
    佾
    0.42
     প্রেসিডেন্ট
    0.42
    ინისტრ
    0.41
    ত
    0.41
    ewnętr
    0.40
    POSITIVE LOGITS
     verticals
    0.43
     වර්ග
    0.43
     ril
    0.42
     teng
    0.41
     makanan
    0.40
     quintessential
    0.40
    สาม
    0.40
     unaltered
    0.40
     hairdryer
    0.40
     leather
    0.40
    Activations Density 0.016%

    No Known Activations