© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 6958
    Prev
    Next
    INDEX
    Explanations

    frequent but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    呢
    0.84
    뭡
    0.78
    нями
    0.75
    ുകയായിരുന്നു
    0.72
    ými
    0.68
    ními
    0.67
     भने
    0.65
     zudem
    0.62
     учетом
    0.62
    اء
    0.60
    POSITIVE LOGITS
     but
    6.59
    but
    6.02
     nhưng
    5.50
    But
    5.31
     But
    5.27
    但
    5.27
     pero
    5.24
     लेकिन
    4.96
     BUT
    4.88
     ولكن
    4.87
    Activations Density 1.662%

    No Known Activations