© 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. 14847
    Prev
    Next
    INDEX
    Explanations

    positive emojis

    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
    Но
    0.88
    О
    0.87
    Кон
    0.82
    Бе
    0.82
    Б
    0.81
    По
    0.81
    К
    0.79
    Мо
    0.79
    Ма
    0.76
    От
    0.76
    POSITIVE LOGITS
     wavenumber
    0.75
     houden
    0.75
     Chloride
    0.70
     pInBuffer
    0.70
     proveedores
    0.69
    🕖
    0.68
     Gibbs
    0.66
     Phosphate
    0.66
    📔
    0.66
    uskal
    0.66
    Activations Density 0.026%

    No Known Activations