© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 12183
    Prev
    Next
    INDEX
    Explanations

    stay asleep

    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
    StructOf
    0.90
    оло
    0.88
    ول
    0.84
    Ҥ
    0.80
    ాగ
    0.79
    ਾਸ
    0.76
    បញ្ចូល
    0.76
    Otros
    0.75
    ЛИ
    0.74
    )।
    0.73
    POSITIVE LOGITS
    walle
    0.83
    `
    0.82
    我们
    0.78
     wymaga
    0.78
    ţii
    0.76
       
    0.75
     maupun
    0.75
     kalangan
    0.74
     ’
    0.74
     മുന്‍
    0.74
    Activations Density 0.001%

    No Known Activations