© 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-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1672
    Prev
    Next
    INDEX
    Explanations

    Belgium and Brussels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    ógio
    1.71
     плана
    1.64
    dler
    1.62
     lược
    1.58
    널
    1.58
     يل
    1.55
    ーパー
    1.54
     îl
    1.53
     Mosby
    1.53
     uitge
    1.52
    POSITIVE LOGITS
     Belgium
    1.72
    Belgium
    1.68
    7
    1.67
    Brussels
    1.63
    8
    1.63
    3
    1.59
    Bel
    1.57
    6
    1.49
    4
    1.49
    Salam
    1.47
    Activations Density 0.347%

    No Known Activations