© 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. 9279
    Prev
    Next
    INDEX
    Explanations

    continent locations and names

    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
    д
    1.27
    з
    1.04
    г
    1.02
    ם
    1.02
    к
    0.98
    ຈະ
    0.98
    ל
    0.95
    ঃ
    0.91
    ном
    0.89
    ки
    0.89
    POSITIVE LOGITS
    (
    1.58
     continent
    1.33
     Continent
    1.30
    -
    1.13
     Europe
    1.08
     Africa
    1.05
    大陸
    1.04
    _
    0.99
    <0x0D>
    0.98
    <0x80>
    0.98
    Activations Density 0.003%

    No Known Activations