© 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. 771
    Prev
    Next
    INDEX
    Explanations

    arrow symbols

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

    formal greetings and good wishes

    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
     neuroscience
    0.33
     typically
    0.32
     programmer
    0.32
     %)
    0.32
    يسي
    0.31
     követ
    0.30
     stratum
    0.30
    ▃
    0.30
     administrat
    0.30
     Neuroscience
    0.30
    POSITIVE LOGITS
     うん
    0.35
     लवली
    0.34
    дино
    0.34
    こんばんは
    0.33
     whirl
    0.33
     Rabb
    0.33
    <<<<
    0.33
     शुरुआ
    0.32
     Boa
    0.32
    MING
    0.32
    Activations Density 0.001%

    No Known Activations