© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1134
    Prev
    Next
    INDEX
    Explanations

    elaborate or delve deeper

    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
     discounted
    0.64
     q
    0.61
     left
    0.61
     kind
    0.59
     <
    0.59
     completed
    0.59
     thousands
    0.59
     {\
    0.56
     otherwise
    0.56
     millions
    0.56
    POSITIVE LOGITS
    卤
    1.07
    €
    1.06
    œil
    1.06
    Olivier
    1.06
    PROBLEM
    1.04
    峣
    1.04
    avaient
    1.03
    utiliser
    1.03
    婼
    1.02
    humidité
    1.02
    Activations Density 0.201%

    No Known Activations