© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69902
    Prev
    Next
    INDEX
    Explanations

    plotly and interactive visualizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    ssystem
    0.88
    斥
    0.83
    rarea
    0.75
     banks
    0.75
    しくて
    0.75
     overworked
    0.74
     desal
    0.70
    hebung
    0.69
    brack
    0.68
     rewarded
    0.66
    POSITIVE LOGITS
    plotly
    1.97
     plotly
    1.87
     웹
    1.71
     tiktok
    1.67
    웹
    1.58
     Konzert
    1.58
     webinar
    1.55
     NDC
    1.54
     TikTok
    1.54
     FGFR
    1.52
    Activations Density 0.008%

    No Known Activations