© 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. 134607
    Prev
    Next
    INDEX
    Explanations

    Nursing care, market data, special features

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

    remember the anatomy

    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
    窅
    0.52
    স্তর
    0.51
    োজেন
    0.51
    𝐦
    0.50
    偐
    0.50
     αφ
    0.49
     နောက်
    0.49
    ouk
    0.48
    inoj
    0.47
    êts
    0.47
    POSITIVE LOGITS
     conjugate
    0.48
     conjugated
    0.46
    -
    0.46
     behem
    0.45
    ar
    0.43
     homic
    0.43
     DUI
    0.42
     leafy
    0.41
     ehe
    0.40
     greasy
    0.40
    Activations Density 0.000%

    No Known Activations