© 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. 74327
    Prev
    Next
    INDEX
    Explanations

    most prominent

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

    ETA or status indicator

    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
    ل
    0.48
    ீ
    0.45
    뉩
    0.45
    म
    0.44
    HN
    0.43
    Delicious
    0.43
    え
    0.43
    取材
    0.42
    ある
    0.42
    り
    0.42
    POSITIVE LOGITS
     Paryayvachi
    0.55
     अवलंब
    0.51
     பின்பற்ற
    0.50
     सर्वाधिक
    0.49
    ẳ
    0.49
     приорите
    0.48
     функ
    0.47
     প্রবল
    0.47
    燡
    0.47
    ಮಾನ
    0.46
    Activations Density 0.000%

    No Known Activations