© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11644
    Prev
    Next
    INDEX
    Explanations

    foundation award prize

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

    numbers or specific library names

    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
    ㅣ
    0.46
     jednak
    0.41
     」,
    0.41
     unters
    0.39
     odre
    0.39
     "))
    0.38
    ؟؟
    0.38
    ofar
    0.38
     "/"
    0.37
     ],
    0.37
    POSITIVE LOGITS
    Diese
    0.43
    বুদ্ধ
    0.39
     பேச்சு
    0.39
    ккей
    0.38
    ρης
    0.37
     pieno
    0.36
    propelled
    0.36
    宣告
    0.36
    spell
    0.35
    此处
    0.35
    Activations Density 0.418%

    No Known Activations