© 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-16K
    7. 2676
    Prev
    Next
    INDEX
    Explanations

    family relationships

    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_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
    י
    0.92
    ﺎ
    0.89
    verständlich
    0.89
     يناير
    0.86
    Те
    0.86
    yards
    0.85
    Κα
    0.85
    ي
    0.85
    İN
    0.84
    Вы
    0.83
    POSITIVE LOGITS
    er
    1.15
    ل
    0.92
    р
    0.91
    н
    0.89
    ка
    0.87
    ر
    0.86
    र
    0.82
    х
    0.82
    ,
    0.82
    artige
    0.82
    Activations Density 0.037%

    No Known Activations