© 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. 16-GEMMASCOPE-2-RES-262K
    7. 14463
    Prev
    Next
    INDEX
    Explanations

    California laws or locations

    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_16_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
    dwyd
    0.57
    anı
    0.55
    PPI
    0.54
     Saha
    0.54
    an
    0.54
    Cz
    0.53
     அச்ச
    0.53
    ᾳ
    0.53
    ut
    0.53
     Guwahati
    0.53
    POSITIVE LOGITS
    California
    1.31
     California
    1.30
     Californians
    1.25
     Californian
    1.18
     california
    1.16
     Kaliforn
    1.09
     CALIFORNIA
    1.05
     Californ
    0.95
     californ
    0.91
     Californie
    0.86
    Activations Density 0.090%

    No Known Activations