© 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. 18334
    Prev
    Next
    INDEX
    Explanations

    order necessary, reporting suspicious, work, output, listen well

    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
     любовь
    0.52
     статистика
    0.50
     люблю
    0.48
    venuto
    0.48
    рів
    0.48
    рики
    0.48
    ವರು
    0.47
    ц
    0.46
    切り
    0.45
     LOVE
    0.45
    POSITIVE LOGITS
    Socket
    0.44
     もの
    0.43
    .(\
    0.43
    >:
    0.43
     multim
    0.42
     treaties
    0.42
     mnemonic
    0.42
    sockets
    0.42
     mắc
    0.41
    :";
    0.41
    Activations Density 0.000%

    No Known Activations