© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53269
    Prev
    Next
    INDEX
    Explanations

    German "is" or "are"

    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
    ت
    0.65
    т
    0.53
     を
    0.52
    ви
    0.52
     tuleb
    0.52
    {
    0.52
    ా
    0.52
    ються
    0.51
    is
    0.50
    ו
    0.50
    POSITIVE LOGITS
     blevet
    0.71
     geweest
    0.59
     a
    0.57
     součástí
    0.54
     готовы
    0.51
     very
    0.48
     очень
    0.48
     able
    0.48
     natürlich
    0.48
     Natürlich
    0.48
    Activations Density 0.028%

    No Known Activations