© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116325
    Prev
    Next
    INDEX
    Explanations

    jump on

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

    The neuron is triggered by the verb “jump” (in forms like “jumped,” “jumping,” or “jump”) in contexts such as “jumped on,” “jumped in,” or “jumped right into.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UARIO
    -0.88
     mutually
    -0.87
     tenuta
    -0.85
     เจ
    -0.84
     другом
    -0.83
    ärer
    -0.83
     metà
    -0.82
    érance
    -0.82
     Firmen
    -0.81
     успеха
    -0.81
    POSITIVE LOGITS
     jumped
    2.05
    jump
    1.94
     jump
    1.91
     jumps
    1.88
    Jump
    1.83
     Jump
    1.80
     jumping
    1.77
     Jumps
    1.71
    jumping
    1.68
     Jumping
    1.61
    Activations Density 0.007%

    No Known Activations