© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10899
    Prev
    Next
    INDEX
    Explanations

    listing items

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

    following lists

    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_40_width_16k_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
     மற்றொரு
    0.51
    两者
    0.50
     begge
    0.49
     sogen
    0.48
     suatu
    0.47
     другую
    0.47
    某个
    0.46
    "]])
    0.46
     другому
    0.46
    后者
    0.45
    POSITIVE LOGITS
    分别是
    1.19
    分别为
    1.09
     क्रमश
    1.04
     যথ
    1.02
     क्रमशः
    0.98
    依次
    0.92
    分別
    0.88
     следующих
    0.83
    分别
    0.82
    以下の
    0.77
    Activations Density 0.845%

    No Known Activations