© 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. 17040
    Prev
    Next
    INDEX
    Explanations

    mathematical function definition

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

    functions and derivatives

    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
    র্ষি
    0.46
    が好き
    0.45
     savent
    0.42
     hates
    0.41
    новение
    0.41
     hota
    0.39
    🖕
    0.38
     mencion
    0.38
     maju
    0.38
    िफिकेट
    0.38
    POSITIVE LOGITS
     ж
    0.46
    一开始
    0.45
    จากการ
    0.42
    렸
    0.42
    đồng
    0.42
     من
    0.41
    樀
    0.40
    㖩
    0.40
    ومن
    0.40
     বিশ্রাম
    0.39
    Activations Density 0.000%

    No Known Activations