© 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. 13515
    Prev
    Next
    INDEX
    Explanations

    membership

    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
    ༈
    0.65
     coarsely
    0.65
    }>{
    0.64
    σιμοποι
    0.62
     зри
    0.58
    Therates
    0.57
     ግ
    0.55
     szcz
    0.55
    🫢
    0.55
     христи
    0.54
    POSITIVE LOGITS
     Membership
    1.19
     membership
    1.14
    会員
    1.12
    Membership
    1.09
    membership
    1.07
     Legislative
    1.02
     Advocacy
    1.02
     Chapters
    1.00
    会员
    0.98
     Convention
    0.97
    Activations Density 0.256%

    No Known Activations