© 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. 169758
    Prev
    Next
    INDEX
    Explanations

    religious beliefs to embroidery to names

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

    GitHub, attacking, territory

    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
    س
    0.54
    ー
    0.52
    ن
    0.51
    こんにちは
    0.50
    ..
    0.47
    入
    0.47
    ات
    0.46
    ！！！！
    0.46
    嗖
    0.46
     Precip
    0.45
    POSITIVE LOGITS
     கிரக
    0.48
     preclude
    0.46
    isle
    0.45
     davranış
    0.44
    ével
    0.43
     বিষয়টি
    0.43
     цей
    0.42
    ξύ
    0.42
     credential
    0.42
    wesen
    0.42
    Activations Density 0.000%

    No Known Activations