© 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. 11688
    Prev
    Next
    INDEX
    Explanations

    code, data, books, or communication

    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
     on
    0.89
    L
    0.86
    一
    0.85
     de
    0.84
    G
    0.83
     be
    0.82
    會
    0.82
    H
    0.82
     On
    0.75
     one
    0.74
    POSITIVE LOGITS
    isering
    0.97
    groupby
    0.91
    tter
    0.89
    ры
    0.85
    ۔
    0.84
    них
    0.84
    ᑉ
    0.84
    li
    0.81
    naye
    0.79
    ”।
    0.79
    Activations Density 0.440%

    No Known Activations