© 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. 32365
    Prev
    Next
    INDEX
    Explanations

    machine wash cold

    np_acts-logits-general · gemini-2.5-flash-lite

    machine washable instructions

    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
    やか
    0.55
    史
    0.46
    IFIC
    0.46
    。",
    0.45
    න්ත
    0.45
    ｽ
    0.45
     служ
    0.45
    ；
    0.44
    찼
    0.44
     парт
    0.42
    POSITIVE LOGITS
     Laz
    0.43
    inee
    0.41
     প্রতী
    0.41
     সবগুলো
    0.38
     Theoretically
    0.37
     fanden
    0.37
     genomes
    0.37
     ক্ষেত্রেই
    0.37
    Alles
    0.37
     જેટ
    0.37
    Activations Density 0.002%

    No Known Activations