© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6089
    Prev
    Next
    INDEX
    Explanations

    lying on your back

    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_12_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
    구성
    0.89
     Rég
    0.88
    讓你
    0.88
     magnifique
    0.87
     不过
    0.87
    让你
    0.83
    围
    0.83
    Raven
    0.82
    Аль
    0.80
     Ā
    0.80
    POSITIVE LOGITS
    reements
    0.95
     direta
    0.81
    bursements
    0.81
    s
    0.80
     auftreten
    0.79
     maio
    0.78
     antitumor
    0.78
    ずに
    0.71
    stelling
    0.70
    amenti
    0.69
    Activations Density 0.000%

    No Known Activations