© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6199
    Prev
    Next
    INDEX
    Explanations

    unwanted thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ụ
    0.51
     spa
    0.51
    关系
    0.51
     Lagrangian
    0.51
     gua
    0.50
     popular
    0.49
     زمین
    0.48
     Sac
    0.48
    ť
    0.48
     Spa
    0.47
    POSITIVE LOGITS
     thoughts
    2.08
     Thoughts
    1.85
    Thoughts
    1.79
     pensamientos
    1.71
    thoughts
    1.66
     Gedanken
    1.48
     мысли
    1.38
     pensamiento
    1.27
     વિચારો
    1.26
     thought
    1.23
    Activations Density 0.493%

    No Known Activations