© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9085
    Prev
    Next
    INDEX
    Explanations

    African startups

    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_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
    தான
    0.42
    >\
    0.41
    buffer
    0.40
     Periodic
    0.40
    簍
    0.39
     Gesamt
    0.39
    quartz
    0.39
    퀼
    0.39
     accret
    0.39
    immune
    0.38
    POSITIVE LOGITS
     Nigerian
    0.83
     Nigerians
    0.75
     Nigeria
    0.75
    Nigerian
    0.71
     Ghanaian
    0.68
    Nigeria
    0.66
     gospel
    0.65
     nigeria
    0.65
     WhatsApp
    0.64
     Gospel
    0.63
    Activations Density 0.051%

    No Known Activations