© 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. 12918
    Prev
    Next
    INDEX
    Explanations

    "it was a" / "is it a"

    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
     هیڅ
    0.43
    ững
    0.43
    arrêt
    0.39
    رسٹ
    0.39
    𐰺
    0.39
    膏
    0.38
     व्यव
    0.38
    ｯ
    0.38
    atost
    0.38
    जनबी
    0.38
    POSITIVE LOGITS
     a
    0.70
     an
    0.66
     from
    0.54
     về
    0.50
     something
    0.50
     berupa
    0.49
     From
    0.47
     about
    0.47
     for
    0.47
    จากการ
    0.47
    Activations Density 0.052%

    No Known Activations