© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125281
    Prev
    Next
    INDEX
    Explanations

    Bulgaria, BGN, favorable tax

    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
     бол
    0.43
     threx
    0.41
     Bulgarian
    0.41
     બે
    0.40
    GISLATIVE
    0.39
     Cnemidophorus
    0.39
     Madhya
    0.38
    楕
    0.38
    metic
    0.38
     Bulgaria
    0.38
    POSITIVE LOGITS
    isRunning
    0.44
    ссив
    0.39
    Window
    0.38
     véhicules
    0.38
     หน่วย
    0.38
     véhicule
    0.38
     veículos
    0.38
     vehículos
    0.38
     szá
    0.37
     inelastic
    0.37
    Activations Density 0.003%

    No Known Activations