© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228088
    Prev
    Next
    INDEX
    Explanations

    clothing, washing, tidying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     interação
    0.47
     dinâmica
    0.45
     ligação
    0.45
     situação
    0.44
     grieving
    0.44
     waarbij
    0.43
    :</
    0.43
     vermiş
    0.43
     yanında
    0.43
     aonde
    0.43
    POSITIVE LOGITS
    washing
    0.47
    clothing
    0.46
    written
    0.46
     ਦਵਾਈ
    0.46
     legislation
    0.44
    最初に
    0.43
     &
    0.43
    USER
    0.43
    tidy
    0.43
    title
    0.43
    Activations Density 0.001%

    No Known Activations