© 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. 99803
    Prev
    Next
    INDEX
    Explanations

    filed under

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

    AI content and websites

    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
    يث
    0.45
    列表
    0.44
    িক্স
    0.43
     $
    0.42
     jer
    0.41
    状况
    0.41
    漏
    0.40
    ू
    0.40
    省略
    0.39
    最
    0.39
    POSITIVE LOGITS
     seguenti
    0.50
     ⏮
    0.48
     sampe
    0.47
     самому
    0.47
     તેમના
    0.47
    ئے۔
    0.47
    തെ
    0.46
     Зараз
    0.45
     (?,
    0.45
     apie
    0.45
    Activations Density 0.000%

    No Known Activations