© 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. 14371
    Prev
    Next
    INDEX
    Explanations

    categories of things

    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
    hetamine
    0.64
    രായി
    0.63
    一个个
    0.61
    Chapters
    0.55
    额
    0.55
     miejsca
    0.55
    links
    0.52
    🇼
    0.52
    Points
    0.51
    stof
    0.51
    POSITIVE LOGITS
     cancers
    1.49
     liquors
    1.43
     sciences
    1.40
     cheeses
    1.39
     wines
    1.38
     soils
    1.37
     energies
    1.36
     sugars
    1.34
     manures
    1.34
     meats
    1.33
    Activations Density 0.250%

    No Known Activations