© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7695
    Prev
    Next
    INDEX
    Explanations

    Indeed

    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_12_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
    ндар
    1.91
    та
    1.77
    тів
    1.74
     ribbed
    1.65
    スの
    1.63
    т
    1.61
     dov
    1.55
    вої
    1.48
    ಾಯ
    1.47
     handouts
    1.47
    POSITIVE LOGITS
    못
    2.28
    ovanje
    2.23
    ۹
    2.13
    ieť
    2.06
    k
    1.98
     परिणामस्वरूप
    1.98
     costituito
    1.94
    ك
    1.94
    bz
    1.93
    ال
    1.91
    Activations Density 0.008%

    No Known Activations