© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31796
    Prev
    Next
    INDEX
    Explanations

    Kosovo and related regions

    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_40_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
     মরু
    0.49
     Nintendo
    0.44
    ﾇ
    0.42
    Desert
    0.42
    沙漠
    0.41
     Rajasthan
    0.40
     Camel
    0.40
    ecoin
    0.40
     রামগতি
    0.39
     Trichodesmium
    0.39
    POSITIVE LOGITS
     Kosovo
    1.25
    Kos
    1.13
     Albanian
    1.01
     Kos
    0.99
     kos
    0.90
    🇽
    0.84
    Alban
    0.83
     Serbian
    0.80
     Albania
    0.74
     Prist
    0.73
    Activations Density 0.002%

    No Known Activations