© 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. 15631
    Prev
    Next
    INDEX
    Explanations

    un-, corruption, infrequent

    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
     scorn
    0.57
     judging
    0.57
     ಐ
    0.54
     ダ
    0.53
    ర్చు
    0.53
     disdain
    0.52
    负
    0.52
     ノー
    0.51
     ノ
    0.50
    iter
    0.50
    POSITIVE LOGITS
     bud
    0.58
    갑습니다
    0.57
    ക്കാന്‍
    0.56
    COMPILE
    0.54
     trời
    0.54
     Pendidikan
    0.54
     পরিবেশ
    0.53
     Eh
    0.51
    )+\
    0.50
     прибыль
    0.50
    Activations Density 0.000%

    No Known Activations