© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10473
    Prev
    Next
    INDEX
    Explanations

    position and layering

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

    absolute positioning

    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
    লাইন
    0.43
     გამოი
    0.40
    uristic
    0.40
    TextAlign
    0.39
     достат
    0.39
    盽
    0.39
     Hollis
    0.38
    ahraga
    0.38
    쥴
    0.38
     JobList
    0.37
    POSITIVE LOGITS
     z
    1.08
     Z
    0.84
     ز
    0.84
    absolute
    0.83
     top
    0.82
    top
    0.82
    zIndex
    0.79
    position
    0.78
     absolute
    0.76
    z
    0.76
    Activations Density 0.014%

    No Known Activations