© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14357
    Prev
    Next
    INDEX
    Explanations

    sequence indicators

    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
    Бо
    0.93
    e
    0.89
    В
    0.87
    Role
    0.86
    g
    0.86
    Ба
    0.86
    Ві
    0.85
     と
    0.84
    Д
    0.84
    Бе
    0.84
    POSITIVE LOGITS
    ковые
    1.02
     distinguishers
    1.00
     infestations
    0.93
     сеть
    0.85
     ткань
    0.84
     будто
    0.84
     эм
    0.83
     spectrometers
    0.82
     zvlá
    0.82
     axioms
    0.82
    Activations Density 0.002%

    No Known Activations