© 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. 14008
    Prev
    Next
    INDEX
    Explanations

    warn of risks

    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
    ㅋㅋㅋㅋ
    0.96
    ㅋㅋㅋ
    0.93
    --
    0.91
     lmao
    0.90
     ㅋㅋ
    0.89
     вроде
    0.88
    ㅋㅋ
    0.86
    みたいな
    0.85
     :/
    0.84
    っぽい
    0.83
    POSITIVE LOGITS
     utilizing
    0.97
     می‌باشد
    0.96
     Utilizing
    0.91
     thru
    0.89
    ことにより
    0.87
     الغير
    0.82
     insuring
    0.81
     todays
    0.80
    utilizzo
    0.78
    不断的
    0.77
    Activations Density 0.176%

    No Known Activations