© 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. 44116
    Prev
    Next
    INDEX
    Explanations

    using directives

    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
     niche
    1.49
     prosent
    1.47
     мүмк
    1.36
    र
    1.36
     effic
    1.33
    гаа
    1.30
     convo
    1.30
     remover
    1.29
    ן
    1.29
     wives
    1.28
    POSITIVE LOGITS
    ل
    1.91
    د
    1.85
    ians
    1.59
    anden
    1.48
    يء
    1.45
    یت
    1.41
     питания
    1.37
    ри
    1.36
    nants
    1.35
    n
    1.34
    Activations Density 0.003%

    No Known Activations