© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6207
    Prev
    Next
    INDEX
    Explanations

    names of towns and cities

    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_22_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
    쟤
    0.70
     anderes
    0.69
     alebo
    0.69
     which
    0.69
     기본
    0.68
     where
    0.67
    ordeel
    0.67
     or
    0.66
     nebo
    0.66
    걔
    0.66
    POSITIVE LOGITS
     town
    1.93
     مدينة
    1.79
     village
    1.63
     cidade
    1.59
     towns
    1.55
     городе
    1.49
     villages
    1.48
     città
    1.48
     ciudad
    1.47
     hamlet
    1.47
    Activations Density 0.063%

    No Known Activations