© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 526
    Prev
    Next
    INDEX
    Explanations

    changing or controlling situations

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

    The neuron strongly activates on verbs that denote changing, altering, or reversing a state.

    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_24_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
    irah
    0.45
    ۲
    0.42
    मा
    0.42
    ين
    0.40
     ٢
    0.40
     وکړئ
    0.40
    弊社
    0.39
    وال
    0.39
     unui
    0.38
     அதிகரி
    0.38
    POSITIVE LOGITS
     그것
    0.45
     ruth
    0.44
    /'
    0.43
     ή
    0.43
     hoặc
    0.43
     или
    0.42
     ఆయన
    0.41
     hắn
    0.41
     იგი
    0.41
     его
    0.40
    Activations Density 0.000%

    No Known Activations