© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    geographic locations and regions

    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
     documental
    0.74
     regard
    0.70
     vessel
    0.70
     against
    0.68
    蜍
    0.67
    m
    0.66
     posteriori
    0.66
     j
    0.66
     похід
    0.66
     relations
    0.66
    POSITIVE LOGITS
     neighborhoods
    1.45
     города
    1.42
     neighbourhoods
    1.37
     zipcode
    1.35
     California
    1.34
     suburban
    1.33
     localities
    1.32
     cities
    1.32
     país
    1.31
     Ontario
    1.31
    Activations Density 0.459%

    No Known Activations