© 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. 15836
    Prev
    Next
    INDEX
    Explanations

    specific names or terms

    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
     ≠
    0.59
     soi
    0.58
     unreliable
    0.57
     প্রভাবশালী
    0.54
     transcoding
    0.54
    (":")[
    0.53
     конкурс
    0.52
     tag
    0.52
     reprogram
    0.52
     masker
    0.52
    POSITIVE LOGITS
    Berkeley
    0.59
    histos
    0.54
    Wilson
    0.54
    стого
    0.54
     AUTHORS
    0.53
    均
    0.52
     исто
    0.52
    elmi
    0.51
    청
    0.51
    AJ
    0.51
    Activations Density 0.000%

    No Known Activations