© 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-262K
    7. 5204
    Prev
    Next
    INDEX
    Explanations

    health properties and research

    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_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
     KFC
    0.90
     trong
    0.86
     sont
    0.84
     הוא
    0.83
     Therap
    0.81
    ların
    0.80
    rugula
    0.80
    𝐽
    0.79
     sebagai
    0.78
     chưa
    0.78
    POSITIVE LOGITS
    ت
    0.89
     замет
    0.79
     acclaimed
    0.78
    تها
    0.77
    zeitig
    0.73
    হ
    0.72
     extrema
    0.71
     inspiración
    0.71
    told
    0.69
     targeted
    0.68
    Activations Density 0.000%

    No Known Activations