© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11481
    Prev
    Next
    INDEX
    Explanations

    breast and chest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    𝐫
    2.72
    𝒑
    2.71
    𝒍
    2.69
    𝒐
    2.58
    𝐜
    2.58
    𝒅
    2.55
    きました
    2.54
     Run
    2.50
    𝒄
    2.46
    𝐥
    2.46
    POSITIVE LOGITS
     lép
    2.78
     élevés
    2.66
    zám
    2.61
     chắn
    2.59
    もり
    2.57
    कुंठ
    2.57
     llena
    2.54
     shelves
    2.52
     sloping
    2.50
    й
    2.49
    Activations Density 0.019%

    No Known Activations