© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3653
    Prev
    Next
    INDEX
    Explanations

    explaining outcomes and causes

    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_24_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
    MaxPooling
    0.61
     workstations
    0.59
    ‎
    0.58
    émica
    0.58
    organisms
    0.57
    ۔
    0.57
    ponents
    0.55
    ostructures
    0.54
    と呼ばれる
    0.54
    。
    0.54
    POSITIVE LOGITS
     haberse
    0.66
     only
    0.65
     ఎవ
    0.64
     THAT
    0.63
     seinem
    0.63
     just
    0.61
     insisted
    0.59
     hadn
    0.57
     ALSO
    0.57
     absoluta
    0.57
    Activations Density 0.105%

    No Known Activations