© 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. 244879
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     jīn
    0.48
     acompañada
    0.47
     pública
    0.45
     elec
    0.44
     karyawan
    0.42
     policial
    0.42
    렬
    0.40
    ēl
    0.40
     ilustración
    0.39
    ूती
    0.39
    POSITIVE LOGITS
    Strategy
    0.53
    Les
    0.51
    Strategies
    0.50
    Vers
    0.49
    ت
    0.48
    Added
    0.48
    т
    0.47
     ثاني
    0.47
    Nah
    0.46
    Hlav
    0.46
    Activations Density 0.001%

    No Known Activations