© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83437
    Prev
    Next
    INDEX
    Explanations

    regions and countries

    np_acts-logits-general · gemini-2.5-flash-lite

    applied to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     சேவை
    0.49
    ՛
    0.45
     ış
    0.44
     प्रबंधन
    0.43
    ée
    0.42
    ፨
    0.42
     हाम्रो
    0.42
    ToProps
    0.42
    ʷ
    0.42
    ług
    0.41
    POSITIVE LOGITS
     mainland
    0.44
     countries
    0.41
     refunds
    0.40
     bonuses
    0.40
     ONLY
    0.39
     refunded
    0.39
     regions
    0.38
     ANOTHER
    0.38
     counties
    0.38
     neighboring
    0.38
    Activations Density 0.003%

    No Known Activations