© 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. 102526
    Prev
    Next
    INDEX
    Explanations

    family and personal relationships

    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
     receivable
    0.43
    樹
    0.42
    山田
    0.41
    質問
    0.40
    史上
    0.40
    न्दावन
    0.40
     misunderstood
    0.39
    ϳ
    0.39
    ทะเบียน
    0.39
    ख्ती
    0.39
    POSITIVE LOGITS
     إن
    0.51
     incest
    0.49
     [
    0.48
     Approximate
    0.48
     পোর্ট
    0.48
    pura
    0.48
     зв
    0.47
     свя
    0.47
    ksi
    0.46
     Agro
    0.46
    Activations Density 0.000%

    No Known Activations