© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13541
    Prev
    Next
    INDEX
    Explanations

    people's conditions or actions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     spoj
    0.58
     byte
    0.57
    佯
    0.55
    目光
    0.54
    コー
    0.53
    relationship
    0.53
     নির্যাতন
    0.52
    历
    0.52
     ถาม
    0.51
     BYTE
    0.51
    POSITIVE LOGITS
    শন
    0.64
    ुका
    0.58
     showered
    0.57
    uated
    0.56
    REW
    0.56
     eet
    0.55
     გამ
    0.54
     खुश
    0.54
    țional
    0.53
     vacaciones
    0.53
    Activations Density 0.000%

    No Known Activations