© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21634
    Prev
    Next
    INDEX
    Explanations

    refresh rate

    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_all/layer_41_width_262k_l0_big
    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
    馔
    0.46
    ByMerging
    0.46
    胱
    0.45
    VED
    0.44
    bauen
    0.43
    kében
    0.43
    灘
    0.43
    र्ने
    0.43
    鹸
    0.42
    бири
    0.42
    POSITIVE LOGITS
     rate
    1.38
     frequency
    1.34
     Rate
    1.34
     Frequency
    1.26
    频率
    1.23
    Rate
    1.22
     frequencies
    1.20
    rate
    1.17
    Frequency
    1.13
    frequency
    1.12
    Activations Density 0.008%

    No Known Activations