© 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
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3466
    Prev
    Next
    INDEX
    Explanations

    code structure following `If` or `json`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.57
    诚信
    0.55
    ↵↵↵↵↵↵↵↵
    0.53
    </a>
    0.53
     \
    0.52
     ser
    0.50
     উভয়
    0.50
    ↵↵↵↵↵↵↵↵↵↵
    0.50
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.50
     小物
    0.49
    POSITIVE LOGITS
     Similar
    0.69
    Similar
    0.68
    Leave
    0.64
     similar
    0.63
    Snippet
    0.58
    similar
    0.58
     Whale
    0.57
    Recursive
    0.57
     similaire
    0.57
    ഞ്ഞ്
    0.56
    Activations Density 0.000%

    No Known Activations