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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24840
    Prev
    Next
    INDEX
    Explanations

    Br prefix words

    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
    ួក
    0.42
     aplicando
    0.40
     iyo
    0.40
    NGTH
    0.40
    礙
    0.40
    viving
    0.39
    こちら
    0.39
    bohyd
    0.38
     thrombo
    0.38
    equivalence
    0.38
    POSITIVE LOGITS
     Br
    0.98
    Br
    0.88
     BR
    0.84
     br
    0.81
    br
    0.74
     Brü
    0.74
     브
    0.70
     Brut
    0.70
     ब्र
    0.70
     Бра
    0.70
    Activations Density 0.005%

    No Known Activations