© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191121
    Prev
    Next
    INDEX
    Explanations

    mask noise study constraints

    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_40_width_262k_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
     uranium
    0.39
    ́
    0.38
     Bear
    0.38
    awatt
    0.37
     UAE
    0.37
     Dud
    0.37
    ett
    0.36
    etime
    0.36
    etr
    0.36
    ujud
    0.35
    POSITIVE LOGITS
     szy
    0.38
     посы
    0.38
    iebel
    0.36
    过渡
    0.36
    <
    0.35
    =$\
    0.35
    gede
    0.35
    BoolVar
    0.35
    ଭ
    0.35
    ছন
    0.34
    Activations Density 0.000%

    No Known Activations