© 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. 106760
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts

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

    jokes that rely on prejudice

    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
     simplification
    0.46
     गोवि
    0.44
     consisting
    0.43
    多样
    0.40
    บาท
    0.40
    ऩे
    0.40
    <0x93>
    0.39
    งาม
    0.39
     competencies
    0.39
     различ
    0.38
    POSITIVE LOGITS
    in
    0.56
     彼
    0.55
     聞い
    0.53
     hear
    0.50
     vecchia
    0.50
     ಅದು
    0.50
     ಅದನ್ನು
    0.49
     actes
    0.49
     ಮೂಲ
    0.48
    ➝
    0.48
    Activations Density 0.000%

    No Known Activations