© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6307
    Prev
    Next
    INDEX
    Explanations

    keywords and colons

    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
    วัสดี
    0.41
    ຯ
    0.41
     extol
    0.39
    esco
    0.39
    ক্রান্ত
    0.39
     priceless
    0.38
    iladi
    0.38
     plast
    0.37
     touristic
    0.37
     devour
    0.37
    POSITIVE LOGITS
    不仅
    0.41
    :`
    0.41
     ARTICLE
    0.40
     гор
    0.39
     гром
    0.39
     голос
    0.38
     liên
    0.38
     предмет
    0.38
     健康
    0.38
     Боль
    0.37
    Activations Density 0.005%

    No Known Activations