© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 29029
    Prev
    Next
    INDEX
    Explanations

    Spring Initializr URL

    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
    d
    0.85
    t
    0.83
    z
    0.81
    da
    0.68
    deki
    0.68
    to
    0.67
    ból
    0.66
    g
    0.65
    should
    0.64
    dés
    0.64
    POSITIVE LOGITS
     costume
    0.54
     COLLEGE
    0.54
     maternity
    0.53
     chromosomal
    0.52
    ⴼ
    0.52
     костю
    0.51
     college
    0.50
     silver
    0.50
     COST
    0.50
     modulated
    0.50
    Activations Density 0.000%

    No Known Activations