© 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. 40-GEMMASCOPE-2-RES-262K
    7. 205099
    Prev
    Next
    INDEX
    Explanations

    use of methods

    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_40_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
     mandala
    0.40
    လမ်း
    0.40
    <unused28>
    0.40
     विद्या
    0.39
     slippery
    0.39
     princípio
    0.39
     intricacies
    0.38
     expediency
    0.38
     Pathways
    0.38
    洱
    0.38
    POSITIVE LOGITS
     obtain
    0.43
    vér
    0.39
    pt
    0.39
    du
    0.38
    curl
    0.38
     ছাড়া
    0.38
     Qualified
    0.38
     नाबाद
    0.38
    todos
    0.37
     notar
    0.37
    Activations Density 0.003%

    No Known Activations