© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3673
    Prev
    Next
    INDEX
    Explanations

    South Africa

    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_16k_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
     pprint
    0.76
    じゃ
    0.70
     কই
    0.69
     Є
    0.67
    SupportActionBar
    0.66
    ሜ
    0.65
    螺
    0.64
     લ
    0.64
     союз
    0.64
    ಕ್ಕೆ
    0.63
    POSITIVE LOGITS
     Johannesburg
    2.11
     Gauteng
    1.99
     Cape
    1.97
    Cape
    1.95
     Pretoria
    1.93
     South
    1.91
     Durban
    1.89
     KwaZulu
    1.88
     Afrika
    1.80
    South
    1.79
    Activations Density 0.081%

    No Known Activations