© 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. 97893
    Prev
    Next
    INDEX
    Explanations

    births and family members

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

    linear regression, neural models

    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
    יר
    0.54
     शाहिद
    0.50
     बिक्री
    0.49
     giấc
    0.49
    苖
    0.45
    ώ
    0.44
    >(&
    0.44
     सेमीफाइनल
    0.44
    सामान्य
    0.43
    轺
    0.43
    POSITIVE LOGITS
    0.55
    SK
    0.47
    hitung
    0.46
    Bin
    0.45
    R
    0.45
    vr
    0.43
    SM
    0.43
    of
    0.42
    valuate
    0.42
     {
    0.42
    Activations Density 0.000%

    No Known Activations