© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 109051
    Prev
    Next
    INDEX
    Explanations

    behind you, her, my

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
     સ
    0.58
     പഴയ
    0.55
     నిర్మాణ
    0.54
     menjaga
    0.50
     Даже
    0.50
     Запа
    0.50
     কপি
    0.50
     даже
    0.50
     ஆ
    0.49
     노
    0.49
    POSITIVE LOGITS
    o
    0.51
    op
    0.51
    िस
    0.47
    otid
    0.47
    ᵗ
    0.47
    us
    0.46
    rao
    0.46
     Devi
    0.46
    :
    0.45
    és
    0.45
    Activations Density 0.000%

    No Known Activations