© 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. 15627
    Prev
    Next
    INDEX
    Explanations

    bedrooms

    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
    via
    0.54
    Via
    0.54
    ర్చు
    0.54
    eleration
    0.53
    faq
    0.53
    棰
    0.51
    Expansion
    0.51
    Integration
    0.50
    複合
    0.50
    Entry
    0.50
    POSITIVE LOGITS
     plus
    0.85
     плюс
    0.83
     +
    0.79
     PLUS
    0.76
     $+$
    0.75
     $+\
    0.75
     each
    0.72
     प्लस
    0.72
     apiece
    0.72
    ＋
    0.72
    Activations Density 0.036%

    No Known Activations