© 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. 245567
    Prev
    Next
    INDEX
    Explanations

    insurance, labor, agreements, graph

    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
     longstanding
    0.51
    วรร
    0.50
    zler
    0.45
    brooke
    0.43
    髅
    0.41
    colgroup
    0.41
    幼児
    0.40
     Benson
    0.39
    澤
    0.39
    רץ
    0.39
    POSITIVE LOGITS
     नती
    0.52
     Pair
    0.50
     Schnitt
    0.48
     resultante
    0.47
    Uma
    0.46
    新的
    0.46
     Eles
    0.45
    ViewModels
    0.45
    有两种
    0.45
    电压
    0.45
    Activations Density 0.001%

    No Known Activations