© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3829
    Prev
    Next
    INDEX
    Explanations

    html head sections

    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_16_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
    льнявыя
    0.58
     (
    0.57
    asinya
    0.54
     অবশ্য
    0.52
    ites
    0.52
    في
    0.52
    it
    0.50
     که
    0.50
    رض
    0.50
    ጪ
    0.50
    POSITIVE LOGITS
     fün
    0.68
    ône
    0.62
     Ư
    0.61
    𝟯
    0.57
     mètres
    0.54
     wooden
    0.52
     soulful
    0.52
     five
    0.52
     deck
    0.52
     Fuß
    0.52
    Activations Density 0.120%

    No Known Activations