© 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. 66933
    Prev
    Next
    INDEX
    Explanations

    hazardous

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

    percentage to decimal conversion

    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
     وہی
    0.46
    獲
    0.46
    標準
    0.46
    ियल
    0.45
    ܥ
    0.45
    وم
    0.45
    埒
    0.44
    ارات
    0.44
    երը
    0.43
    ビー
    0.42
    POSITIVE LOGITS
     emailed
    0.48
    链接
    0.45
    anço
    0.44
     அல்லது
    0.43
     табле
    0.43
     ссылку
    0.43
    📃
    0.43
     texto
    0.43
    ].
    0.42
    ຕໍ່
    0.42
    Activations Density 0.000%

    No Known Activations