© 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. 31-GEMMASCOPE-2-RES-262K
    7. 84601
    Prev
    Next
    INDEX
    Explanations

    specific subjects and their explanations

    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_31_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
    voja
    0.50
     zeich
    0.48
    ۔
    0.47
    dimensional
    0.45
    be
    0.45
     meist
    0.43
    idimensional
    0.43
    薩
    0.42
    eyes
    0.42
    集团
    0.42
    POSITIVE LOGITS
     Waterman
    0.46
     reclama
    0.46
     {//
    0.46
     Imo
    0.45
     Artwork
    0.45
     Trong
    0.45
     сигнала
    0.45
     TCP
    0.45
     warmest
    0.44
     a
    0.44
    Activations Density 0.006%

    No Known Activations