© 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. 240121
    Prev
    Next
    INDEX
    Explanations

    expertise in specialized areas

    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
     buvo
    0.52
    事业单位
    0.50
    iee
    0.48
     세제곱
    0.44
     cbind
    0.43
     सार्वजनिक
    0.43
     trae
    0.43
    ে
    0.43
     मिड
    0.42
    大陆
    0.42
    POSITIVE LOGITS
    لس
    0.52
     minimizes
    0.48
     maximizes
    0.47
     متخصص
    0.47
    في
    0.46
    графия
    0.45
    maximizing
    0.44
     prevents
    0.43
     реша
    0.42
     بحيث
    0.42
    Activations Density 0.001%

    No Known Activations