© 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. 5815
    Prev
    Next
    INDEX
    Explanations

    Indian languages and culture

    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
    িনবার্গ
    0.55
    রত্ব
    0.45
    स्करण
    0.43
    पाउंड
    0.43
    𝘺
    0.42
    வ்வேறு
    0.42
    वरणीय
    0.41
    ंपरिक
    0.41
    म्प्ट
    0.41
     usamos
    0.40
    POSITIVE LOGITS
     Madhya
    0.47
     lakhs
    0.47
     Rajasthan
    0.43
     Bharatiya
    0.43
     samaj
    0.43
     Gandhiji
    0.41
     Uttar
    0.40
     Samaj
    0.40
     ਤ
    0.40
     Bhojpuri
    0.40
    Activations Density 0.018%

    No Known Activations