© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11423
    Prev
    Next
    INDEX
    Explanations

    left side

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in spotting step-by-step exercise or stretch instructions phrased as imperatives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    োলন
    0.51
    鑾
    0.50
    崁
    0.50
    icially
    0.49
    伍章
    0.48
     Dewey
    0.48
    спу
    0.48
    薹
    0.48
     intermediate
    0.48
     حدث
    0.47
    POSITIVE LOGITS
    左
    2.30
    LeftSide
    2.22
     왼쪽
    2.17
     左
    2.13
     LEFT
    2.11
     left
    2.08
     Left
    2.08
    Left
    2.06
    left
    1.99
     왼
    1.96
    Activations Density 0.597%

    No Known Activations