© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78471
    Prev
    Next
    INDEX
    Explanations

    Apple Watch

    np_acts-logits-general · gemini-2.5-flash-lite

    conversation starters and acknowledgements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     sleep
    0.54
     slept
    0.52
    睡眠
    0.51
    、
    0.50
    實
    0.50
    αν
    0.47
    Sleep
    0.47
     asleep
    0.45
    睡
    0.45
    さと
    0.44
    POSITIVE LOGITS
    குழந்த
    0.55
     Salam
    0.48
    î
    0.47
     ஆகியவற்ற
    0.47
     बांग्लादेश
    0.47
    ır
    0.46
     फुटबॉल
    0.45
    öne
    0.45
     janë
    0.45
     Selamat
    0.44
    Activations Density 0.001%

    No Known Activations