© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2081
    Prev
    Next
    INDEX
    Explanations

    marine organisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Citibank
    0.74
    airport
    0.72
    삵
    0.71
     falcon
    0.70
     Mahindra
    0.70
     glfw
    0.69
    鷹
    0.69
    傈
    0.68
    obao
    0.68
     Pontiac
    0.67
    POSITIVE LOGITS
     worms
    1.67
     worm
    1.52
     mollus
    1.51
     invertebrate
    1.48
     nemat
    1.47
     invertebrates
    1.44
     larvae
    1.42
    worms
    1.42
     Worm
    1.41
     jellyfish
    1.41
    Activations Density 0.222%

    No Known Activations