© 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. 20956
    Prev
    Next
    INDEX
    Explanations

    erosion

    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
     ("
    0.66
    ö
    0.57
    "]]
    0.56
    している
    0.54
    ("
    0.52
    /"
    0.50
     Corporations
    0.49
     (
    0.49
    ",
    0.49
    ريم
    0.49
    POSITIVE LOGITS
    瞅
    0.68
    erosion
    0.65
     erosion
    0.65
     piccoli
    0.58
    ínsula
    0.54
     eroding
    0.54
    Whi
    0.54
     dents
    0.53
    નની
    0.53
     deple
    0.53
    Activations Density 0.006%

    No Known Activations