© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16059
    Prev
    Next
    INDEX
    Explanations

    how things function or fit

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

    easy to use, control, and see

    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_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
     Xiaomi
    0.62
     ২০২২
    0.57
     nano
    0.53
     xia
    0.52
    youtube
    0.50
     Xiao
    0.50
     gadget
    0.50
    🥰
    0.49
     Youtube
    0.49
     nanos
    0.49
    POSITIVE LOGITS
    㛲
    0.52
    鉻
    0.47
    玨
    0.47
    ียง
    0.44
    況
    0.44
    鶯
    0.42
    লিখ
    0.41
    ﻹ
    0.41
    ρή
    0.41
    鐘
    0.40
    Activations Density 0.352%

    No Known Activations