© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6484
    Prev
    Next
    INDEX
    Explanations

    movement into

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

    The neuron detects occurrences of the verb “jump” (in all its forms).

    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
    ㊙
    0.60
    тися
    0.59
    MinIntensity
    0.59
    弑
    0.56
    穩定
    0.54
     안정
    0.54
     ঘণ্টায়
    0.54
     वेजिट
    0.53
    رسٹ
    0.53
     يكن
    0.52
    POSITIVE LOGITS
     jump
    1.92
    jump
    1.91
     jumps
    1.81
     jumping
    1.76
     Jump
    1.75
    Jump
    1.73
     leap
    1.70
     jumped
    1.70
     Jumping
    1.69
    跳
    1.66
    Activations Density 0.171%

    No Known Activations