© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10593
    Prev
    Next
    INDEX
    Explanations

    Nigeria, Nigerian, Abuja, Lagos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
     পাহাড়
    0.46
    柬
    0.46
    လုပ်
    0.45
     インド
    0.42
    ℚ
    0.42
    劵
    0.42
    タル
    0.42
     券
    0.42
    ರ್ಶ
    0.41
     হুগলী
    0.40
    POSITIVE LOGITS
     Nigeria
    1.27
     Nigerian
    1.26
    Nigeria
    1.17
     Nigerians
    1.12
     Abuja
    1.12
    Nigerian
    1.10
     nigeria
    1.09
     Lagos
    1.09
     niger
    1.02
     Kaduna
    1.02
    Activations Density 0.001%

    No Known Activations