© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88802
    Prev
    Next
    INDEX
    Explanations

    experienc, definition, sun, born, sodium

    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
    ens
    0.51
    applications
    0.50
    Chen
    0.48
     autos
    0.48
    Auto
    0.47
    J
    0.45
    Types
    0.45
    咱们
    0.44
     CNRS
    0.44
    ovane
    0.44
    POSITIVE LOGITS
    х
    0.59
    ҳ
    0.55
    риал
    0.55
     полуо
    0.54
    т
    0.52
    жие
    0.52
    као
    0.51
     જો
    0.50
    ц
    0.48
    ходят
    0.47
    Activations Density 0.000%

    No Known Activations