© 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. 15657
    Prev
    Next
    INDEX
    Explanations

    multilingual authors

    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
    𝘬
    0.53
     fox
    0.51
    开车
    0.50
     HEAT
    0.50
    MPT
    0.49
     CRYST
    0.49
    ,}
    0.49
     அஜித்
    0.48
     calm
    0.48
    త్
    0.47
    POSITIVE LOGITS
     authors
    0.64
    authors
    0.63
     author
    0.58
     Authors
    0.57
    ὗ
    0.55
    ﺌ
    0.55
    author
    0.54
    anh
    0.54
    চির
    0.54
    दूसरी
    0.54
    Activations Density 0.000%

    No Known Activations