© 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. 29-GEMMASCOPE-2-RES-65K
    7. 4139
    Prev
    Next
    INDEX
    Explanations

    expedition, trekking, exploring, adventure

    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_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
    🎠
    0.87
     manipul
    0.80
    🍣
    0.75
    gür
    0.75
    🎹
    0.74
    波動
    0.74
     뮤
    0.74
     musicales
    0.73
     algorit
    0.72
    帘
    0.71
    POSITIVE LOGITS
     expedition
    2.29
     expeditions
    2.21
     Expedition
    1.96
     экспеди
    1.85
     trekking
    1.62
     treks
    1.57
     trek
    1.55
     adventure
    1.49
     expedi
    1.48
     explorers
    1.48
    Activations Density 0.152%

    No Known Activations