© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 804
    Prev
    Next
    INDEX
    Explanations

    flow of

    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
    seated
    0.88
     spheres
    0.76
    etano
    0.75
    っくり
    0.74
     үй
    0.73
     сидя
    0.72
     sphere
    0.72
    耄
    0.71
     স্ট্যান্ড
    0.70
    クラウド
    0.70
    POSITIVE LOGITS
     connecting
    2.17
    connecting
    1.85
     Connecting
    1.84
    Connecting
    1.82
     connect
    1.70
     connects
    1.66
     linking
    1.63
    蜿
    1.63
     passing
    1.61
     crossing
    1.61
    Activations Density 1.222%

    No Known Activations