Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 81
    Prev
    Next
    INDEX
    Explanations

    cleaning, conditioning, blending actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ید
    0.46
     wisata
    0.38
    ۰
    0.38
     \
    0.37
     یا
    0.36
     cupid
    0.35
    не
    0.34
    یا
    0.34
     علی
    0.34
     hiyo
    0.34
    POSITIVE LOGITS
    و
    0.63
    at
    0.50
    ي
    0.50
    ת
    0.49
    त
    0.48
    تي
    0.46
    د
    0.46
    י
    0.45
    ו
    0.45
    લ
    0.44
    Activations Density 4.032%

    No Known Activations