© 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. 75326
    Prev
    Next
    INDEX
    Explanations

    investment and labour

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

    numbers and delimiters

    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
     repurposed
    0.52
    平和
    0.46
    raž
    0.45
     Libre
    0.45
    ழ்
    0.43
     Bearded
    0.43
    ：「
    0.42
    ȋ
    0.42
     முற்றிலும்
    0.41
    类似于
    0.41
    POSITIVE LOGITS
     bize
    0.50
    ہر
    0.45
     кто
    0.44
     당신
    0.43
     هات
    0.43
     قلي
    0.43
     хто
    0.43
     telephones
    0.42
    に戻
    0.42
     منا
    0.42
    Activations Density 0.000%

    No Known Activations