© 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. 5845
    Prev
    Next
    INDEX
    Explanations

    sociological, societal, social

    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
     হইলাম
    0.52
    \{(
    0.51
     recited
    0.51
    บคุม
    0.50
     "'"
    0.49
     полю
    0.49
    ジナル
    0.49
     মন্ত্রণালয়ের
    0.48
    ुस्तान
    0.48
     sırada
    0.47
    POSITIVE LOGITS
     natoque
    0.73
    democratic
    0.64
     العلمي
    0.63
     nauk
    0.61
    ǃ
    0.61
     κοινων
    0.60
     Nyl
    0.60
     স্তর
    0.59
    ্যাপ
    0.58
    ቡ
    0.58
    Activations Density 0.109%

    No Known Activations