© 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. 169804
    Prev
    Next
    INDEX
    Explanations

    varied contexts

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

    negative prompts to exclude unwanted styles

    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
     chống
    0.55
     pasaj
    0.52
    তিন
    0.50
    旸
    0.49
     cỡ
    0.47
     WeChat
    0.47
     alınan
    0.47
    主角
    0.47
    氢
    0.46
     কিছুক্ষণ
    0.46
    POSITIVE LOGITS
    бах
    0.44
    seits
    0.43
    自信
    0.41
    हार
    0.40
    Jobs
    0.40
    vika
    0.40
    이어
    0.40
     varied
    0.39
    EXAMPLES
    0.39
     Reforms
    0.39
    Activations Density 0.002%

    No Known Activations