© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2791
    Prev
    Next
    INDEX
    Explanations

    Italian nationality and context

    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
     Selangor
    0.79
    ::
    0.74
     Spokane
    0.73
    ጉ
    0.73
     Saskatoon
    0.72
     Jaan
    0.72
     Bromley
    0.71
    ģ
    0.69
    ローブ
    0.68
     NSTX
    0.68
    POSITIVE LOGITS
     Italian
    2.78
    Italian
    2.67
    Italy
    2.59
     Italy
    2.59
    意大利
    2.52
     итальян
    2.50
     italian
    2.49
     Italians
    2.48
     italien
    2.41
     Italia
    2.40
    Activations Density 0.131%

    No Known Activations