© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8819
    Prev
    Next
    INDEX
    Explanations

    African apes and places

    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
    Negative Logits
     İstanbul
    0.92
    İstanbul
    0.90
     sprink
    0.89
     İzmir
    0.89
    boston
    0.83
     Sz
    0.82
     windmills
    0.82
     Glendale
    0.82
     sz
    0.82
    埙
    0.81
    POSITIVE LOGITS
     Congolese
    2.34
     Congo
    2.23
     Kongo
    1.81
     Ebola
    1.71
     Rwandan
    1.67
     African
    1.65
     gorilla
    1.62
     Gabon
    1.62
     Cameroon
    1.61
     Ugandan
    1.60
    Activations Density 0.077%

    No Known Activations