© 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. 10644
    Prev
    Next
    INDEX
    Explanations

    using something to achieve a purpose

    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
     χρησιμοποι
    0.49
    を使う
    0.47
     பயன்படுத்து
    0.45
     ಬಳಸ
    0.44
    を使用
    0.44
    r
    0.42
     используя
    0.41
    を利用
    0.41
     استخدم
    0.41
    ใช้
    0.40
    POSITIVE LOGITS
    ع
    0.47
    ق
    0.45
     the
    0.38
     it
    0.38
     their
    0.38
    ці
    0.36
    ها
    0.34
    ная
    0.34
    தி
    0.34
     your
    0.33
    Activations Density 0.121%

    No Known Activations