© 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. 3569
    Prev
    Next
    INDEX
    Explanations

    this way

    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
    ంలోని
    0.38
    ictive
    0.37
     باول
    0.37
     землі
    0.36
    名の
    0.35
     Allgemeinen
    0.35
    新たに
    0.35
    ("/
    0.35
     முதல்
    0.34
     ನಗರ
    0.34
    POSITIVE LOGITS
     this
    0.72
     melakukannya
    0.70
     этом
    0.70
     hacerlo
    0.64
     этого
    0.64
     này
    0.62
    这样做
    0.61
     هذا
    0.61
     это
    0.58
     tohoto
    0.58
    Activations Density 0.627%

    No Known Activations