© 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. 145282
    Prev
    Next
    INDEX
    Explanations

    do not

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

    feeling prepared

    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
     Weibo
    0.55
     instagram
    0.53
     🎉
    0.52
     😘
    0.52
     Treas
    0.51
     เรา
    0.51
     เพิ่ม
    0.50
     삶
    0.50
     ダイ
    0.50
     divent
    0.49
    POSITIVE LOGITS
    فظ
    0.39
    湁
    0.39
     بهذا
    0.39
    Flora
    0.38
     connectors
    0.38
    éget
    0.38
     connector
    0.38
    協議
    0.38
    ून
    0.37
    义务
    0.37
    Activations Density 0.000%

    No Known Activations