© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11395
    Prev
    Next
    INDEX
    Explanations

    what do you want to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deformation
    0.30
     ਮ
    0.29
     \[
    0.29
     बतौर
    0.29
     menacing
    0.29
    kode
    0.29
    projekt
    0.29
     セ
    0.29
     hypnot
    0.28
     Ար
    0.28
    POSITIVE LOGITS
    取决于
    0.40
    있는
    0.38
    할
    0.38
    있다
    0.35
    됩니다
    0.35
    에게
    0.34
    있
    0.34
    谁
    0.33
    奇怪
    0.33
    也
    0.33
    Activations Density 0.092%

    No Known Activations