© 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. 31-GEMMASCOPE-2-RES-262K
    7. 50616
    Prev
    Next
    INDEX
    Explanations

    Los Angeles and California

    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_31_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
     Belarusian
    0.45
     birch
    0.44
     panch
    0.43
    圩
    0.43
     Bangladesh
    0.42
     Halifax
    0.42
     snow
    0.42
     Belarus
    0.41
     pjes
    0.41
    ([]
    0.41
    POSITIVE LOGITS
     California
    1.77
    California
    1.77
     Californian
    1.53
     Californians
    1.52
     CALIFORNIA
    1.44
     Kaliforn
    1.44
     californ
    1.42
     Californie
    1.41
     california
    1.40
     Californ
    1.34
    Activations Density 0.084%

    No Known Activations