© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11441
    Prev
    Next
    INDEX
    Explanations

    my default

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

    default 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
    relatively
    0.39
     ねえ
    0.38
    ㊗
    0.38
    pregn
    0.37
    severe
    0.37
     októ
    0.35
    laugh
    0.35
    lebih
    0.35
     項
    0.35
     विकल्पों
    0.35
    POSITIVE LOGITS
     my
    0.63
    my
    0.58
    我的
    0.58
     DEFAULT
    0.55
    myt
    0.54
    mym
    0.54
     default
    0.53
    MY
    0.53
     Default
    0.52
    myapp
    0.52
    Activations Density 0.078%

    No Known Activations