© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15737
    Prev
    Next
    INDEX
    Explanations

    interaction

    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
     inflationary
    0.63
     calendars
    0.59
    úč
    0.56
    ایج
    0.56
     flavors
    0.53
    曆
    0.53
    ukt
    0.52
    воз
    0.52
     overestimate
    0.52
    퀘
    0.52
    POSITIVE LOGITS
    NCC
    0.60
     NCC
    0.60
    yar
    0.57
     Nor
    0.57
     LEVEL
    0.56
     เรือ
    0.55
     Nar
    0.54
    interaction
    0.54
    getLevel
    0.54
     NMC
    0.54
    Activations Density 0.000%

    No Known Activations