© 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. 117748
    Prev
    Next
    INDEX
    Explanations

    cause

    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
    ي
    0.57
    އ
    0.55
    ल
    0.55
    l
    0.54
    Ги
    0.52
    يز
    0.51
    li
    0.50
     l
    0.50
    សូម
    0.49
    作为
    0.49
    POSITIVE LOGITS
     splashing
    0.57
     aerobic
    0.55
     hibernation
    0.54
     resounding
    0.53
     inhibition
    0.53
     surrounding
    0.52
     regeneration
    0.52
     distraction
    0.51
     confinement
    0.50
    latent
    0.50
    Activations Density 0.000%

    No Known Activations