© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15562
    Prev
    Next
    INDEX
    Explanations

    industry

    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
     hermoso
    0.73
     پشتی
    0.65
     시민
    0.64
     ふ
    0.63
    推薦
    0.63
     इतिहासकारों
    0.63
    ɲ
    0.61
     pomocy
    0.60
     अम्ब
    0.60
     destek
    0.59
    POSITIVE LOGITS
     OEMs
    1.13
    Industry
    1.10
     industry
    1.06
     foodservice
    1.06
     Industry
    1.05
    industry
    1.05
     CFO
    1.01
    ꯠ
    1.00
     CIO
    0.98
     Coatings
    0.96
    Activations Density 0.236%

    No Known Activations