Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 3603
    Prev
    Next
    INDEX
    Explanations

    Catalonia, Barcelona, Catalan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
     Ashland
    0.69
    هُ
    0.68
     চূ
    0.65
     ち
    0.65
     Appropriation
    0.65
     Ted
    0.63
     Hein
    0.63
     ја
    0.63
    ʁ
    0.62
     gist
    0.62
    POSITIVE LOGITS
    Barcelona
    1.53
     Catalan
    1.51
     Catalonia
    1.47
     Barcelona
    1.44
     Catalunya
    1.42
     catal
    1.39
    Catal
    1.39
     katal
    1.24
     Barcelone
    1.23
     Catal
    1.23
    Activations Density 0.124%

    No Known Activations