© 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. 15026
    Prev
    Next
    INDEX
    Explanations

    code structure parsing

    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
     OK
    0.68
     ok
    0.61
     Ok
    0.61
    Ok
    0.57
     Alright
    0.56
    ()?;
    0.56
     ок
    0.55
    学
    0.55
    okhttp
    0.54
    ابت
    0.54
    POSITIVE LOGITS
    sru
    0.59
     Manu
    0.59
    Manu
    0.57
     ब्यू
    0.56
    firetruck
    0.56
     autonomously
    0.54
    Specific
    0.54
     देशमुख
    0.53
    ণু
    0.53
    舅
    0.53
    Activations Density 0.072%

    No Known Activations