© 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-16K
    7. 12789
    Prev
    Next
    INDEX
    Explanations

    start or condition

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

    fixed or predictable information

    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_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
    ص
    0.40
     வி
    0.38
     Asking
    0.38
    і
    0.38
     راس
    0.38
    vist
    0.37
    Asking
    0.37
    上
    0.37
    自我
    0.37
    Berlin
    0.36
    POSITIVE LOGITS
     wreath
    0.50
     wreaths
    0.50
    amorph
    0.49
     garland
    0.49
     titleImageUrl
    0.49
     mousse
    0.49
    onglet
    0.48
    ीकृत
    0.46
    zyg
    0.45
     bruise
    0.45
    Activations Density 0.001%

    No Known Activations