© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9028
    Prev
    Next
    INDEX
    Explanations

    Casablanca, nitric acid, Ninja Turtles, Hay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     cotisation
    1.19
     Ciudad
    1.19
    Changing
    1.18
     〢
    1.17
    Currency
    1.17
    Vendor
    1.16
    Expense
    1.15
    Footer
    1.15
    ╿
    1.15
    ILING
    1.15
    POSITIVE LOGITS
     ref
    0.77
     permit
    0.74
     extermin
    0.71
     faults
    0.71
     matter
    0.70
     explain
    0.69
     fault
    0.69
     holds
    0.68
     sh
    0.68
     disrupt
    0.67
    Activations Density 0.002%

    No Known Activations