© 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. 1407
    Prev
    Next
    INDEX
    Explanations

    explanations and improvements

    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
     нам
    0.59
    ”)
    0.57
    ↵↵↵
    0.57
     diduga
    0.54
    ↵
    0.53
    ↵↵
    0.53
    ")
    0.49
    ↵↵↵↵↵
    0.49
    ↵↵↵↵↵↵↵
    0.48
    歟
    0.48
    POSITIVE LOGITS
    Cómo
    0.75
    cómo
    0.71
    How
    0.69
    What
    0.68
     Advantages
    0.66
     여러
    0.66
     วิธี
    0.66
    Important
    0.65
     What
    0.64
    Robust
    0.64
    Activations Density 0.176%

    No Known Activations