© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 76438
    Prev
    Next
    INDEX
    Explanations

    context-free or context-aware

    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
     হাইড্রোক
    0.47
    ிருக்கும்
    0.46
     hydrochloric
    0.45
    おります
    0.45
    </thead>
    0.43
     grayish
    0.43
    熟
    0.43
     reasonably
    0.42
     isoniazid
    0.41
    TBL
    0.40
    POSITIVE LOGITS
    ті
    0.47
    æ
    0.47
    🇳
    0.46
    é
    0.45
     في
    0.45
     tudo
    0.45
     meeste
    0.44
     सेवाएं
    0.44
    ú
    0.44
    któ
    0.43
    Activations Density 0.004%

    No Known Activations