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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2569
    Prev
    Next
    INDEX
    Explanations

    classification, requirement, or question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
    ↵
    1.10
     **
    1.02
     [
    0.96
     (
    0.92
     (**
    0.84
     ([
    0.83
     {
    0.79
     specifically
    0.78
     using
    0.77
     st
    0.74
    POSITIVE LOGITS
    me
    1.02
    Clinical
    0.98
    ↳
    0.96
    And
    0.94
    But
    0.93
    Comparison
    0.92
    We
    0.92
    Which
    0.92
    %、
    0.92
    another
    0.92
    Activations Density 0.344%

    No Known Activations